AUTHOR=Xie Zhuofan , Lin Rongbin , Wang Lingzhe , Zhang Anmin , Lin Jiaqing , Tang Xiaoda 

TITLE=Data augmentation and deep neural network classification based on ship radiated noise

JOURNAL=Frontiers in Marine Science

VOLUME=Volume 10 - 2023

YEAR=2023

URL=https://www.frontiersin.org/journals/marine-science/articles/10.3389/fmars.2023.1113224

DOI=10.3389/fmars.2023.1113224

ISSN=2296-7745

ABSTRACT=Various types of ships sail at sea, and identifying maritime ship types through ship-radiated noise is one of the tasks of ocean observation. The ocean environment is complex and changeable, such rapid environmental changes underline the difficulties of obtaining a huge amount of samples. Meanwhile, the length of each sample has a decisive influence on the classification results but there is no universal sampling length selection standard. This study proposes a comprehensive judgment method based on multiple features to select an appropriate sample length. Then, a one-dimensional deep convolution generative adversarial network (1-DDCGAN) model is utilized to augment the training datasets' ship-radiated noise signals to solve the small sample number problem. In order to realize the classification of ship-radiated noise without artificial feature extraction, a one-dimensional convolution neural network (CNN) is designed for ship-radiated noise classification. On this basis, a one-dimensional residual network is designed to improve classification accuracy. Experiments are performed to verify the proposed framework using public datasets. After data augmentation, statistical parameters are used to measure the similarity between the original samples and the generated samples. Then, the generated samples are integrated into the training set. The convergence speed of the network is clearly accelerated, and the classification accuracy is significantly improved in the one-dimensional CNN and ResNet.