Estimation of shell characteristics using time-frequency patterns and neural network

Zakharia, Manell E.; Chevret, Patrick; Magand, F.

doi:10.1109/ultsym.1996.584074

Cited by 3 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The same procedure as used for sediment characterization was then applied to a more complex case with multiple components: the characterization of a sonar target in the free field [19].…”

Section: Inversion Of Sonar Target Characteristicsmentioning

confidence: 99%

Neural network approach for inverting velocity dispersion; application to sediment and to sonar target characterization

Zakharia

Chevret

2000

Inverse Problems

View full text Add to dashboard Cite

A novel inversion method based on a neural network is presented. The parameter used for the inversion is the velocity dispersion of surface acoustic waves. The velocity law is computed using time-frequency representation (Wigner-Ville), which is a highly relevant tool for multi-component dispersive signal analysis. The same inversion method has been applied to two physical cases: inversion of geoacoustical parameters of seabeds and characterization of sonar target properties. The method possesses high accuracy performance (error less than a few per cent) in both cases on either simulated or experimental data. The a priori information used for inversion is very poor and limited to the physical description of the direct problem.

show abstract

“…The same procedure as used for sediment characterization was then applied to a more complex case with multiple components: the characterization of a sonar target in the free field [19].…”

Section: Inversion Of Sonar Target Characteristicsmentioning

confidence: 99%

Neural network approach for inverting velocity dispersion; application to sediment and to sonar target characterization

Zakharia

Chevret

2000

Inverse Problems

View full text Add to dashboard Cite

show abstract

“…Mathematically, the reconstruction of SOS is a nonlinear inverse problem. Many different techniques have been developed to solve this problem, for example, algebraic reconstruction methods [13,22,1], adjoint methods [40,10,11,35], and artificial neural networks (ANN) [45,41,9,25]. Algebraic reconstruction methods are typically computationally quite light methods to solve the inverse problem.…”

Section: Introductionmentioning

confidence: 99%

Model reduction in acoustic inversion by artificial neural network

Koponen,

Lähivaara,

Kaipio

et al. 2021

Preprint

View full text Add to dashboard Cite

In ultrasound tomography, the speed of sound inside an object is estimated based on acoustic measurements carried out by sensors surrounding the object. An accurate forward model is a prominent factor for high-quality image reconstruction, but it can make computations far too time-consuming in many applications. Using approximate forward models, it is possible to speed up the computations, but the quality of the reconstruction may have to be compromised. In this paper, a neural network -based approach is proposed, that can compensate for modeling errors caused by the approximate forward models. The approach is tested with various different imaging scenarios in a simulated two-dimensional domain. The results show that with fairly small training data sets, the proposed approach can be utilized to approximate the modelling errors, and to significantly improve the image reconstruction quality in ultrasound tomography, compared to commonly used inversion algorithms.

show abstract

Model reduction in acoustic inversion by artificial neural network

Koponen

Lähivaara

Kaipio

et al. 2021

The Journal of the Acoustical Society of America

View full text Add to dashboard Cite

In ultrasound tomography, the speed of sound inside an object is estimated based on acoustic measurements carried out by sensors surrounding the object. An accurate forward model is a prominent factor for high-quality image reconstruction, but it can make computations far too time-consuming in many applications. Using approximate forward models, it is possible to speed up the computations, but the quality of the reconstruction may have to be compromised. In this paper, a neural network-based approach is proposed that can compensate for modelling errors caused by the approximate forward models. The approach is tested with various different imaging scenarios in a simulated two-dimensional domain. The results show that with fairly small training datasets, the proposed approach can be utilized to approximate the modelling errors, and to significantly improve the image reconstruction quality in ultrasound tomography, compared to commonly used inversion algorithms.

show abstract

Estimation of shell characteristics using time-frequency patterns and neural network

Cited by 3 publications

References 5 publications

Neural network approach for inverting velocity dispersion; application to sediment and to sonar target characterization

Neural network approach for inverting velocity dispersion; application to sediment and to sonar target characterization

Model reduction in acoustic inversion by artificial neural network

Model reduction in acoustic inversion by artificial neural network

Contact Info

Product

Resources

About