Underwater Acoustic Signal Prediction Based on MVMD and Optimized Kernel Extreme Learning Machine

Yang, Huirong; Gao, Lipeng; Li, Guohui

doi:10.1155/2020/6947059

Cited by 15 publications

(8 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the nonlinearity and stochasticity in ocean environments, this would best suit a multi-layered neural network or deep neural network. The multi-parameter dependencies between frequency and absorption favor this higher-complexity machine learning model that optimizes parameter weights in each layer of the neural network through back propagation [43] [42].…”

Section: Machine Learningmentioning

confidence: 99%

Signal Absorption-Based Range Estimator for Undersea Swarms

O’Neill¹

2020

View full text Add to dashboard Cite

Robotic swarms are becoming increasingly complex on the surface and in air due to highspeed and reliable communication links, Global Positioning Satellites (GPS), and visual support to relative navigation. However, the limited propagation of these signals in the ocean has impacted similar advances in undersea robotics. Autonomous underwater vehicles (AUVs) often rely on acoustics to inform navigation solutions; however, this approach presents challenges for scalable robotic swarms. Acoustic navigation is a means to inform range and bearing to a target. Many methods for range and bearing estimation, including current low-cost solutions, rely on precision time synchronization or two-way communication to compute ranges as part of a full navigation solution. The high cost of reliable Chip-scale atomic clocks (CSACs) and acoustic modems relative to other vehicle components limits large-scale swarms due to the associated cost-per-vehicle and communications infrastructure. We propose a single, high-cost vehicle with a reliable navigation solution as a "leader" for a scalable swarm of lower-cost vehicles that receive acoustic signals from a source onboard the lead vehicle using a single hydrophone. These lower-cost "followers" navigate relative to the leader according to the preferred behavioral pattern, but for simplicity, we will refer to a simple following behavior in this work. This thesis outlines a method to obtain range estimates to sound sources in which the signal content, including frequency and power at its origin, can be reasonably approximated. Total transmission loss is calculated based on empirical equations for the absorption of sound in seawater and combined with geometric spreading loss from environmental models to estimate range to a source based on the loss at differential frequencies. We refer to this calculation as the signal absorption-based range estimator (SABRE). This method for obtaining range combines with Doppler-shift methods for target bearing based on the maximum frequency detected within a banded limit around a known source frequency. A primary objective for SABRE is to address techniques that support low-cost options for undersea swarming. This thesis's contributions include a novel method for range estimation onboard underwater autonomous vehicles that supports navigation relative to a known source when combined with Doppler-shift methods for target bearing. This thesis seeks to develop the theory, algorithms, and analytical tools required and apply those tools to real-world data sets to investigate the feasibility, sources of error, and accuracy of this new approach to range estimation for underwater swarms.

show abstract

Section: Machine Learningmentioning

confidence: 99%

Signal Absorption-Based Range Estimator for Undersea Swarms

O’Neill¹

2020

View full text Add to dashboard Cite

show abstract

“…Another hybrid model is based on decomposition, which can decompose data into components of different complexity by introducing a mode decomposition algorithm. Therefore, this kind of model can better capture the inherent characteristics of data and reduce the complexity of original data, so as to achieve a better prediction effect ( Yang et al, 2020 , Wang et al, 2020 ). The hybrid model based on decomposition has been applied in many ways ( Shrivastava et al, 2016 , Wang et al, 2017 , Chu et al, 2021 ).…”

Section: Introductionmentioning

confidence: 99%

A new hybrid prediction model of cumulative COVID-19 confirmed data

Chen

Yang

2022

Process Safety and Environmental Protection

Self Cite

View full text Add to dashboard Cite

“…In recent years, some researches only have been done to optimize the number k of IMFs. For example, if the difference between the mutual information obtained from the reconstructed sequence signal by VMD and the original signal when k = k i and k = k i+1 is less than the threshold, k = k i is chosen to be the appropriate number of IMFs in VMD [26]; the orthogonal value is calculated in terms of the length of data, and the optimal k is to be the value corresponding to the minimum orthogonal value [27]; an adaptive parameter optimized VMD method proposed determines the optimal parameter k by judging the ratio of the center frequencies of two adjacent IMFs [28]. Some researches have also been performed to optimize both these two parameters k and α of VMD.…”

Section: Introductionmentioning

confidence: 99%

Signal Denoising Based on Wavelet Threshold Denoising and Optimized Variational Mode Decomposition

Yan

et al. 2021

Journal of Sensors

View full text Add to dashboard Cite

To eliminate the noise from the signals received by MEMS vector hydrophone, a joint algorithm is proposed in this paper based on wavelet threshold (WT) denoising, variational mode decomposition (VMD) optimized by a hybrid algorithm of Multiverse Optimizer (MVO) and Particle Swarm Optimization (PSO), and correlation coefficient (CC) judgment to perform the signal denoising of MEMS vector hydrophone, named as MVO-PSO-VMD-CC-WT, whose fitness function is the root mean square error (RMSE) and whose individual is the parameters of VMD. For every individual, the original signal is decomposed by VMD into pure components, noisy components, and noise components in terms of CC judgment, where the pure components are directly retained, the noisy components are denoised by WT denoising, and the noise components are discarded, and then, the denoised noisy components and the pure components are reconstructed to be the denoised signal of the original signal. Then, the obtained optimal individual is utilized to perform the signal denoising by MVO-PSO-VMD-CC-WT by the use of the above repeated signal processing. Two simulated experimental results show that the MVO-PSO-VMD-CC-WT algorithm which has the highest signal-to-noise ratio and the least RMSE is superior to the other compared algorithms. And the proposed MVO-PSO-VMD-CC-WT algorithm is effectively applied to perform the signal denoising of the actual lake experiments. Therefore, the proposed MVO-PSO-VMD-CC-WT is suitable for the signal denoising and can be applied into the actual experiments in signal processing.

show abstract

Underwater Acoustic Signal Prediction Based on MVMD and Optimized Kernel Extreme Learning Machine

Cited by 15 publications

References 21 publications

Signal Absorption-Based Range Estimator for Undersea Swarms

Signal Absorption-Based Range Estimator for Undersea Swarms

A new hybrid prediction model of cumulative COVID-19 confirmed data

Signal Denoising Based on Wavelet Threshold Denoising and Optimized Variational Mode Decomposition

Contact Info

Product

Resources

About