Time-scale wavelet scattering using hyperbolic tangent function for vessel sound classification
buir.contributor.author | Çetin, A. Enis | |
buir.contributor.orcid | Çetin, A. Enis|0000-0002-3449-1958 | |
dc.citation.epage | 1798 | en_US |
dc.citation.spage | 1794 | en_US |
dc.contributor.author | Can, Gökmen | en_US |
dc.contributor.author | Akbaş, Cem Emre | en_US |
dc.contributor.author | Çetin, A. Enis | en_US |
dc.coverage.spatial | Kos, Greece | |
dc.date.accessioned | 2018-04-12T11:43:03Z | |
dc.date.available | 2018-04-12T11:43:03Z | |
dc.date.issued | 2017-08-09 | en_US |
dc.department | Department of Electrical and Electronics Engineering | en_US |
dc.description | Date of Conference: 28 Aug.-2 Sept. 2017 | |
dc.description | Conference name: 25th European Signal Processing Conference (EUSIPCO), 2017 | |
dc.description.abstract | We introduce a time-frequency scattering method using hyperbolic tangent function for vessel sound classification. The sound data is wavelet transformed using a two channel filter-bank and filter-bank outputs are scattered using tanh function. A feature vector similar to mel-scale cepstrum is obtained after a wavelet packed transform-like structure approximating the mel-frequency scale. Feature vectors of vessel sounds are classified using a support vector machine (SVM). Experimental results are presented and the new feature extraction method produces better classification results than the ordinary Mel-Frequency Cepstral Coefficients (MFCC) vectors. © EURASIP 2017. | en_US |
dc.description.provenance | Made available in DSpace on 2018-04-12T11:43:03Z (GMT). No. of bitstreams: 1 bilkent-research-paper.pdf: 179475 bytes, checksum: ea0bedeb05ac9ccfb983c327e155f0c2 (MD5) Previous issue date: 2017 | en |
dc.identifier.doi | 10.23919/EUSIPCO.2017.8081518 | en_US |
dc.identifier.uri | http://hdl.handle.net/11693/37531 | en_US |
dc.language.iso | English | en_US |
dc.publisher | IEEE | en_US |
dc.relation.isversionof | http://dx.doi.org/10.23919/EUSIPCO.2017.8081518 | en_US |
dc.source.title | 25th European Signal Processing Conference, EUSIPCO 2017 | en_US |
dc.subject | Hyperbolic tangent function | en_US |
dc.subject | Scattering filter-bank | en_US |
dc.subject | Timefrequency representation | en_US |
dc.subject | Vessel sound classification | en_US |
dc.subject | Classification (of information) | en_US |
dc.subject | Filter banks | en_US |
dc.subject | Hyperbolic functions | en_US |
dc.subject | Image retrieval | en_US |
dc.subject | Signal processing | en_US |
dc.subject | Speech recognition | en_US |
dc.subject | Support vector machines | en_US |
dc.subject | Vectors | en_US |
dc.subject | Classification results | en_US |
dc.subject | Feature extraction methods | en_US |
dc.subject | Hyperbolic tangent function | en_US |
dc.subject | Mel frequencies | en_US |
dc.subject | Mel-frequency cepstral coefficients | en_US |
dc.subject | Sound classification | en_US |
dc.subject | Time-frequency representations | en_US |
dc.subject | Two-channel filter banks | en_US |
dc.subject | Acoustic wave scattering | en_US |
dc.title | Time-scale wavelet scattering using hyperbolic tangent function for vessel sound classification | en_US |
dc.type | Conference Paper | en_US |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- Time-scale wavelet scattering using hyperbolic tangent function for vessel sound classification.pdf
- Size:
- 2.3 MB
- Format:
- Adobe Portable Document Format
- Description:
- Full printable version