Weighted Undirected Similarity Network Construction and Application for Nonlinear Time Series Detection

Wang, Haiyan; Liang, Xuanming; Yan, Ye; Shen, Xiaohong

doi:10.1109/lsp.2023.3286809

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2023

2024

Publication Types

Select...

Article2

Other1

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

CA_MobileNetV2 for Underwater Acoustic Target Recognition

Tian,

Haiyang,

Haiyan

et al. 2023

2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)

View full text Add to dashboard Cite

CA_MobileNetV2 for Underwater Acoustic Target Recognition

Tian,

Haiyang,

Haiyan

et al. 2023

2023 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC)

View full text Add to dashboard Cite

Multiscale Correlation Network and Geodesic Distance for Remote Passive Ship Detection in Marine Environment

Zhang,

Wang,

Yan

et al. 2024

IEEE J. Oceanic Eng.

View full text Add to dashboard Cite

Remote passive acoustic signal detection using multi-scale correlation networks and network spectrum distance in marine environment

Zhang,

Wang,

Liang

et al. 2023

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

Detecting acoustic signals in the ocean is crucial for port and coastal security, but existing methods often require informative priors. This paper introduces a new approach that transforms acoustic signal detection into network characterization using a MCN construction method. The method constructs a network representation of the acoustic signal by measuring pairwise correlations at different time scales. It proposes a network spectrum distance method that combines information geometry and graph signal processing theory to characterize these complex networks. By comparing the spectra of two networks, the method quantifies their similarity or dissimilarity, enabling comparisons of multi-scale correlation networks constructed from different time series data and tracking changes in nonlinear dynamics over time. The effectiveness of these methods is substantiated through comprehensive simulations and real-world data collected from the South China Sea. The results illustrate that the proposed approach attains a significant detection probability of over 90% when the signal-to-noise ratio exceeds −18 dB, whereas existing methods require a signal-to-noise ratio of at least −15 dB to achieve a comparable detection probability. This innovative approach holds promising applications in bolstering port security, facilitating coastal operations, and optimizing offshore activities by enabling more efficient detection of weak acoustic signals.

show abstract

Weighted Undirected Similarity Network Construction and Application for Nonlinear Time Series Detection

Cited by 3 publications

References 22 publications

CA_MobileNetV2 for Underwater Acoustic Target Recognition

CA_MobileNetV2 for Underwater Acoustic Target Recognition

Multiscale Correlation Network and Geodesic Distance for Remote Passive Ship Detection in Marine Environment

Remote passive acoustic signal detection using multi-scale correlation networks and network spectrum distance in marine environment

Contact Info

Product

Resources

About