The underwater acoustic target signal is affected by factors such as the underwater environment and the ship’s working conditions, causing the generalization of the recognition model is essential. This study is devoted to improving the generalization of recognition models, proposing a feature extraction module based on neural network and time-frequency analysis, and validating the feasibility of the model-based transfer learning method. A network-based filter based on one-dimensional convolution is built according to the calculation mode of the finite impulse response filter. An attention-based model is constructed using the convolution network components and full-connection components. The attention-based network utilizes convolution components to perform the Fourier transform and feeds back the optimization gradient of a specific task to the network-based filter. The network-based filter is designed to filter the observed signal for adaptive perception, and the attention-based model is constructed to extract the time-frequency features of the signal. In addition, model-based transfer learning is utilized to further improve the model’s performance. Experiments show that the model can perceive the frequency domain features of underwater acoustic targets, and the proposed method demonstrates competitive performance in various classification tasks on real data, especially those requiring high generalizability.

Moyamoya disease (MMD) is a cerebrovascular disease that is characterized by progressive stenosis or occlusion of the internal carotid arteries and its main branches, which leads to the formation of abnormal small collateral vessels. However, little is known about how these special vascular structures affect cortical network connectivity and brain function. By applying EEG analysis and graphic network analyses undergoing EEG recording of subjects with eyes-closed (EC) and eyes-open (EO) resting states, and working memory (WM) tasks, we examined the brain network features of hemorrhagic (H_MMD) and ischemic MMD (I_MMD) brains. For the first time, we observed that I_MMD had the much lower alpha-blocking rate during EO state than healthy controls while H_MMD exhibited the relatively low EEG activity rate across all the behavior states. Further, I_MMD showed strong network connections in the alpha-wave band in frontal and parietal regions during EO and WM states. EEG frequency and network topological maps during both resting and WM states indicated that the left frontal lobe and left parietal lobe in H_MMD patients and the right parietal lobe and temporal lobe in I_MMD patients have clear differences compared with controls, which provides a new insight to understand distinct electrophysiological features of MMD. However, due to the small sample size of recruited patient subjects, the result conclusion may be limited.

Target classification and recognition have always been complex problems in underwater acoustic signal processing because of noise interference and feature instability. In this paper, a robust feature extraction method based on multi-task learning is proposed, which provides an effective solution. Firstly, an MLP-based network model suitable for underwater acoustic signal processing is proposed to optimize feature extraction. Then, multi-task learning is deployed on the model in hard parameter-sharing so that the model can extract anti-noise interference features and embed prior feature extraction knowledge. In the model training stage, the simultaneous training method enables the model to improve the robustness and representation of classification features with the knowledge of different tasks. Furthermore, the optimized classification features are sent to the classification network to complete target recognition. The proposed method is evaluated by the dataset collected in the real environment. The results show that the proposed method effectively improves recognition accuracy and maintains high performance under different noise levels, which is better than popular methods.