Recognition of Fill Walnuts and Empty Walnuts Using Acoustic Signal Processing

Abstract

An intelligent walnut recognition system combining acoustic emissions analysis, decision tree and fuzzy inference system (FIS) was developed and tested. In data acquisition part, Fast Fourier Transform (FFT) of impact signals was measured. Feature extracted in two ways: Using time domain and FFT of impact signal. 66% of samples used for training and remaining samples used for testing. In selection feature part, most important feature selected that were: average and second frequency amplitude of FFT. The method is based on feature generation by Fast Fourier Transform (FFT) and time domain, produce decision tree with J48 algorithm and classification by fuzzy rules. The output of J48 algorithm was employed to produce the crisp if-then rule and MF (membership function) sets. The structure of FIS classifier was then defined based on the crisp sets. The results showed that the total classification accuracy were 94.68%. The results indicate that the proposed FFT-J48-FIS model can be used in separation fill walnuts from empty walnuts.