Single-channel blind source separation of underwater acoustic signals using improved NMF and FastICA

• DOI: 10.3389/fmars.2022.1097003
• Publication Date: 2023-01-16T05:23:40Z
• Authors: Dawei Li; Minghui Wu; Liang Yu; Jianhui Han; Hao Zhang
• Keywords: FastICA; Non-negative Matrix Factorization; SIGNAL (programming language); Independence; Feature (linguistics)

When automatic monitoring buoys receive mixed acoustic signals from multiple underwater targets, the statistical blind source separation (BSS) task is used to separate and identify vessel features, which overly complex needs improvement, especially noting that noise cancellation stealth technologies are advancing rapidly. To fill this gap in capability, an improved non-negative matrix factorization (NMF) based BSS algorithm built on a FastICA machine learning backbone. With tool, spatial spectral correlation of introduced into NMF by resolve non-convex feature problems commonly encountered contemporary algorithms. Moreover, modulation adaptability increases local expressivity independence decomposed base matrix, proven meet requirements improve effect FastICA. Simulated empirical results show compared with state-of-the-art algorithms, our novel approach obtains better signal-to-noise reduction accuracy while maintaining superior target signal recognition features.