Underwater Reverberation Suppression via Attention and Cepstrum Analysis-Guided Network

Hao, Yukun; Wu, Xiaojun; Wang, Huiyuan; He, X. T.; Chen, Hao; Wang, Zirui; Hu, Qiao

doi:10.3390/jmse11020313

Cited by 5 publications

(3 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This seamlessly incorporates external tools to support computations that surpass the core capabilities of LLMs. Meanwhile, ToolkenGPT [55] adopts a strategy of learning "toolken" embeddings to represent each tool as a token. This empowers LLMs to effortlessly utilize tools similar to generating word tokens.…”

Section: Tool-based Methodsmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the "pre-train, fine-tune" and "pre-train, prompt" paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of prompting on graphs is still limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template, but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt. CCS CONCEPTS• Computing methodologies → Learning latent representations; • Information systems → Data mining.

show abstract

Section: Tool-based Methodsmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

show abstract

“…AI methods, on the other hand, utilize machine learning and deep learning techniques to learn and recognize reverberation features and perform suppression automatically (Hao et al, 2023). By training models with large amounts of data, AI methods can possess more substantial generalization and adaptability, making them capable of handling more complex underwater reverberation environments and signals.…”

Section: The Relationship Between Artificial Intelligence Methods And...mentioning

confidence: 99%

A Wasserstein generative adversarial network with gradient penalty for active sonar signal reverberation suppression

Wang,

Zhang,

Huang

et al. 2023

Front. Mar. Sci.

View full text Add to dashboard Cite

Reverberation is the primary background interference of active sonar systems in shallow water environments, affecting target position detection accuracy. Reverberation suppression is a signal processing technique used to improve the clarity and accuracy of received signals by eliminating the echoes, reverberations, and noise that occur during underwater propagation. Existing reverberation suppression methods include algorithms based on Time-Frequency domain processing, noise reduction, adaptive filtering, and spectral subtraction, but their performance in high-reverberation environments (echo of small targets) still does not meet the requirements of target detection. To address the impact of high reverberation environments, we propose a structural suppression method based on the Wasserstein gradient penalty generative adversarial network (RSWGAN-GP). The reverberation suppression generation network uses a one-dimensional convolutional network structure to process normalized time-domain signals and achieves the reconstruction of the reverberation signal through Encoder-Decoder. The proposed method is verified through accurate and effective data collection during sea trials. Comparative results show that RSWGAN-GP effectively suppresses reverberation in observation signals with multiple bright spots, improving the signal-to-reverberation ratio by approximately 10 dB compared to other excellent algorithms and enhancing the information analysis and feature extraction capabilities of active sonar signals.

show abstract

“…Reverberation is the primary background interference in the active sonar target detection, and a comprehensive understanding of its characteristics and formation mechanism is the key to improving the performance of the active target detection (Cui et al, 2023;Hao et al, 2023). Meanwhile, reverberation carries hidden ocean information that can be used for environmental parameter inversion, leading to the increasing attention toward reverberation research in the field of marine acoustics.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Bottom Reverberation Intensity Under Beam-Controlled Emission Conditions in Deep Water

Zheng,

Guo,

Zhu

et al. 2024

Archives of Acoustics

View full text Add to dashboard Cite

A comprehensive understanding of the characteristics and the formation mechanism of reverberation is the key to improving the performance of the active target detection. In response to the challenge of analyzing the intensity of bottom reverberation in typical deep-sea environments, this study proposes a prediction method for the bottom reverberation intensity under beam-controlled emission conditions. It explains the variation law of bottom reverberation intensity under beam-controlled emission conditions in typical deep-sea environments of the South China Sea through theoretical and simulation analyses. Reverberation intensity of the deep-sea bottom under beam-controlled emission conditions exhibits significant fluctuations during the duration of reverberations in the direct sound zone of the seabed. This phenomenon is closely related to the directionality of the source emission, leading to intermittent reverberation masking and detectable areas in the active sonar detection. In addition, the duration of the high-reverberation zone near the cutoff distance of the direct sound from the seabed is longer under the beam-controlled emission conditions of the emission array located within the surface waveguide layer of the deep sea during winter.

show abstract

Underwater Reverberation Suppression via Attention and Cepstrum Analysis-Guided Network

Cited by 5 publications

References 42 publications

Geography of Technology Transfer in China

Geography of Technology Transfer in China

A Wasserstein generative adversarial network with gradient penalty for active sonar signal reverberation suppression

Analysis of Bottom Reverberation Intensity Under Beam-Controlled Emission Conditions in Deep Water

Contact Info

Product

Resources

About