Library

Using Generative Adversarial Networks to Generate Ultrasonic Signals

Advances in Deep Learning technologies enable Data Driven Modeling as an alternative to classical simulation methods in many application fields. In this work, we are proposing a Deep Learning based Generative Adversarial Network (GAN) to achieve Data Driven Modeling for synthesizing ultrasonic data that can be used in Non-Destructive Evaluation (NDE) applications. GAN uses generator and discriminator networks which are trained to learn patterns and generate B-scans. Preliminary results show close match between the synthesized and real data, highlighting its potential use in NDE simulations.

EngineeringPhysicsComputer Science
View graphSource

Paper

Full text

PDF

Using Generative Adversarial Networks to Generate Ultrasonic Signals

Semantic Scholar · Engineering · 2020

Abstract

Advances in Deep Learning technologies enable Data Driven Modeling as an alternative to classical simulation methods in many application fields. In this work, we are proposing a Deep Learning based Generative Adversarial Network (GAN) to achieve Data Driven Modeling for synthesizing ultrasonic data that can be used in Non-Destructive Evaluation (NDE) applications. GAN uses generator and discriminator networks which are trained to learn patterns and generate B-scans. Preliminary results show close match between the synthesized and real data, highlighting its potential use in NDE simulations.

Source of record · Semantic Scholar

Similar papers

Generating ultrasonic images indistinguishable from real images using Generative Adversarial Networks.L. Posilović, D. Medak, M. Subašić et al.2021 · Ultrasonics · 35 citations In Library
Realistic Ultrasonic Environment Simulation Using Conditional Generative Adversarial NetworksMaximilian Pöpperl, Raghavendra Gulagundi, S. Yogamani et al.2019 · 2019 IEEE Intelligent Vehicles Symposium (IV) · 3 citations In Library
Generative adversarial network with object detector discriminator for enhanced defect detection on ultrasonic B-scansLuka Posilovi'c, D. Medak, M. Subašić et al.2021 · Neurocomputing · 56 citations In Library
A Generative Adversarial Neural Network for Beamforming Ultrasound Images Invited PresentationA. Nair, T. Tran, A. Reiter et al.2019 · Annual Conference on Information Sciences and Systems · 33 citations In Library
UltraDfeGAN: Detail-Enhancing Generative Adversarial Networks for High-Fidelity Functional Ultrasound SynthesisZhuo Li, Xuhang Chen, Shuqiang Wang2025 · arXiv.org · 1 citation In Library
Generative Adversarial Networks: Ultrasound Image TranslationNoah Graff2020 · UWM Digital Commons (University of Wisconsin–Milwaukee) In Library
Side-Scan Sonar Image Synthesis Based on Generative Adversarial Network for Images in Multiple FrequenciesYifan Jiang, Bonhwa Ku, Wan‐Jin Kim et al.2020 · IEEE Geoscience and Remote Sensing Letters · 38 citations In Library
Generalized Generative Deep Learning Models for Biosignal Synthesis and Modality TransferT. Dissanayake, Tharindu Fernando, Simon Denman et al.2022 · IEEE journal of biomedical and health informatics · 33 citations In Library
A Real-Time Medical Ultrasound Simulator Based on a Generative Adversarial Network ModelBo Peng, Xing Huang, Shiyuan Wang et al.2019 · International Conference on Information Photonics · 22 citations In Library
Expansion of restricted sample for underwater acoustic signal based on generative adversarial networksFan Liu, Qingzeng Song, Guanghao Jin2019 · International Conference on Graphic and Image Processing · 10 citations In Library
© 2026 NYSGPT2525 LLC