System for removing shell pieces from hazelnut kernels using impact

6 A system for removing shell pieces from hazelnut kernels using impact vibration analysis was developed 7 in which nuts are dropped onto a steel plate and the vibration signals are captured and analyzed. The 8 melcepstral feature parameters, line spectral frequency values, and Fourier-domain Lebesgue features were 9 extracted from the vibration signals. The best experimental results were obtained using the mel-cepstral 10 feature parameters. The feature parameters were classified using a support vector machine (SVM), which 11 was trained a priori using a manually classified dataset. An average recognition rate of 98.2% was achieved. 12 An important feature of the method is that it is easily trainable, enabling it to be applicable to other nuts, 13 including walnuts and pistachio nuts. In addition, the system can be implemented in real time. 14