Can, GökmenAkbaş, Cem EmreÇetin, A. Enis2018-04-122018-04-122017-08-09http://hdl.handle.net/11693/37531Date of Conference: 28 Aug.-2 Sept. 2017Conference name: 25th European Signal Processing Conference (EUSIPCO), 2017We 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.EnglishHyperbolic tangent functionScattering filter-bankTimefrequency representationVessel sound classificationClassification (of information)Filter banksHyperbolic functionsImage retrievalSignal processingSpeech recognitionSupport vector machinesVectorsClassification resultsFeature extraction methodsHyperbolic tangent functionMel frequenciesMel-frequency cepstral coefficientsSound classificationTime-frequency representationsTwo-channel filter banksAcoustic wave scatteringConference Paper10.23919/EUSIPCO.2017.8081518