Feature Extraction Method for Loudspeaker Abnormal Sound Based on EEMD and Sample Entropy

To classify the loudspeaker abnormal sound more accurately, a feature extraction method is proposed in this paper, in which ensemble empirical mode decomposition (EEMD) and sample entropy are used for feature extraction. Support vector machine (SVM) is used to verify the effectiveness of the proposed method. After preprocessing of fundamental notching, the loudspeaker response is decomposed using EEMD. The intrinsic mode function (IMF) components are selected with correlation analysis and their sample entropy values are calculated to structure the feature vectors. Focused on the classification for loudspeaker abnormal sound with small sample condition, the experiment results have shown that SVM can classify accurately for loudspeaker abnormal sound, and more accurate than SVM using wavelet packets and sample entropy, moreover it achieved 95.33% classification accuracy.