TY - JOUR N2 - A diagnostic technique based on independent component analysis (ICA), fast Fourier transform (FFT), and support vector machine (SVM) is suggested for effectively extracting signal features in infrasound signal monitoring. Firstly, ICA is proposed to separate the source signals of mixed infrasound sources. Secondly, FFT is used to obtain the feature vectors of infrasound signals. Finally, SVM is used to classify the extracted feature vectors. The approach integrates the advantages of ICA in signal separation and FFT to extract the feature vectors. An experiment is conducted to verify the benefits of the proposed approach. The experiment results demonstrate that the classification accuracy is above 98.52% and the run time is only 2.1 seconds. Therefore, the proposed strategy is beneficial in enhancing geophysical monitoring performance. L1 - http://journals.pan.pl/Content/127336/PDF/aoa.2023.145230.pdf L2 - http://journals.pan.pl/Content/127336 PY - 2023 IS - No 2 EP - 199 DO - 10.24425/aoa.2023.145230 KW - independent component analysis KW - fast Fourier transform KW - support vector machine KW - infrasound signal A1 - Lu, Quanbo A1 - Wang, Meng A1 - Li, Mei PB - Polish Academy of Sciences, Institute of Fundamental Technological Research, Committee on Acoustics VL - vol. 48 DA - 2023.05.28 T1 - Infrasound Signal Classification Based on ICA and SVM SP - 191 UR - http://journals.pan.pl/dlibra/publication/edition/127336 T2 - Archives of Acoustics ER -