Research on aquatic biological signal recognition based on mode decomposition and deep learning

Abstract As an important research content in the field of marine biology and ecology, aquatic biological signal (ABS) recognition is of great significance for understanding marine ecosystems, protecting biodiversity, and monitoring environmental changes. To improve the recognition accuracy of ABS, this paper proposes a new ABS recognition method based on mode decomposition and deep learning. First, real ABS data were obtained from the public website, and some data were selected for the simulation experiment. Secondly, the signal is decomposed using improved variational mode decomposition by human evolutionary optimization algorithm, and the decomposed intrinsic mode function (IMF) set is classified into low complexity and high complexity IMF using improved Lempel–Ziv complexity and reverse permutation entropy. Then, mutual information is used to select double eigenvectors from low and high complexity IMF, respectively, and recognition is performed based on the double eigenvectors using weighted-convolutional neural network-bidirectional gate recursive unit-Attention model. Finally, the proposed ABS recognition method is applied to both chaotic and real signals, and additional proof of universality is performed using real signals. The result of the study shows that the accuracy of the proposed method for the recognition of chaotic and real signals is as high as 97.3% and 98.0%. In conclusion, the research on ABS recognition in this paper is successful and has a broad application prospect.