Underwater Acoustic Target Recognition Based on Hilbert–Huang Transform and Data Augmentation

This article proposes an underwater acoustic target recognition method using the Hilbert–Huang transform (HHT) and data augmentation, with a residual convolutional neural network (CNN) as the classifier. The method involves decomposing the signal via empirical mode decomposition, denoising based on the principal component analysis (PCA) algorithm, extracting the HHT spectrum features of underwater acoustic targets, performing data augmentation using a deep convolutional generative adversarial network, and employing a ResNet18 model for recognition. The results of different models, including support vector machine, ordinary CNN, VGG19, and ResNet18 are compared. This article also analyzes and compares the recognition results of different input features, such as Mel-frequency cepstrum coefficient, constant Q transform, HHT spectrum, and HHT marginal spectrum. The results show that the denoising method based on PCA effectively reduces noise and redundancy. Compared to other features, the HHT spectrum provides better recognition accuracy. Data augmentation can significantly improve the accuracy. The residual CNN with the input feature of the HHT spectrum using the data augmentation achieves the best recognition performance, proving effective for recognition at low signal-to-noise ratios. Especially at 0 dB, the recognition accuracy can still reach 90.03%.