Automatic monitoring of group-housed pigs in real time through porcine acoustic signals has played a crucial role in automated\nfarming. In the process of data collection and transmission, acoustic signals are generally interfered with noise. In this paper, an\neffective porcine acoustic signal denoising technique based on ensemble empirical mode decomposition (EEMD), independent\ncomponent analysis (ICA), and wavelet threshold denoising (WTD) is proposed. Firstly, the porcine acoustic signal is\ndecomposed into intrinsic mode functions (IMFs) by EEMD. In addition, permutation entropy (PE) is adopted to distinguish\nnoise-dominant IMFs from the IMFs. Secondly, ICA is employed to extract the independent components (ICs) of the noisedominant\nIMFs. The correlation coefficients of ICs and the first IMF are calculated to recognize noise ICs. The noise ICs will be\nremoved. Then, WTD is applied to the other ICs. Finally, the porcine acoustic signal is reconstructed by the processed components.\nExperimental results show that the proposed method can effectively improve the denoising performance of porcine\nacoustic signal.
Loading....