Machine Learning and Deterministic Approach to the Reflective Ultrasound Tomography
This paper describes the method developed using the Extreme Gradient Boosting (Xgboost) algorithm that allows high-resolution imaging using the ultrasound tomography (UST) signal. More precisely, we can locate, isolate, and use the reflective peaks from the UST signal to achieve high-resolution imag...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/22/7549 |
| _version_ | 1797510493721591808 |
|---|---|
| author | Dariusz Majerek Tomasz Rymarczyk Dariusz Wójcik Edward Kozłowski Magda Rzemieniak Janusz Gudowski Konrad Gauda |
| author_facet | Dariusz Majerek Tomasz Rymarczyk Dariusz Wójcik Edward Kozłowski Magda Rzemieniak Janusz Gudowski Konrad Gauda |
| author_sort | Dariusz Majerek |
| collection | DOAJ |
| description | This paper describes the method developed using the Extreme Gradient Boosting (Xgboost) algorithm that allows high-resolution imaging using the ultrasound tomography (UST) signal. More precisely, we can locate, isolate, and use the reflective peaks from the UST signal to achieve high-resolution images with low noise, which are far more useful for the location of points where the reflection occurred inside the experimental tank. Each reconstruction is divided into two parts, estimation of starting points of wave packets of raw signal (SAT—starting arrival time) and image reconstruction via XGBoost algorithm based on SAT matrix. This technology is the basis of a project to design non-invasive monitoring and diagnostics of technological processes. In this paper, we present a method of the complete solution for monitoring industrial processes. The measurements used in the study were obtained with the author’s solution of ultrasound tomography. |
| first_indexed | 2024-03-10T05:32:18Z |
| format | Article |
| id | doaj.art-2ca4a343b3ec43aaa026550f54f3481a |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T05:32:18Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-2ca4a343b3ec43aaa026550f54f3481a2023-11-22T23:09:57ZengMDPI AGEnergies1996-10732021-11-011422754910.3390/en14227549Machine Learning and Deterministic Approach to the Reflective Ultrasound TomographyDariusz Majerek0Tomasz Rymarczyk1Dariusz Wójcik2Edward Kozłowski3Magda Rzemieniak4Janusz Gudowski5Konrad Gauda6Faculty of Technology Fundamentals, Lublin University of Technology, 20-618 Lublin, PolandInstitute of Computer Science and Innovative Technologies, University of Economics and Innovation in Lublin, 20-209 Lublin, PolandResearch & Development Center Netrix S.A., 20-704 Lublin, PolandFaculty of Management, Lublin University of Technology, 20-618 Lublin, PolandFaculty of Management, Lublin University of Technology, 20-618 Lublin, PolandInstitute of Computer Science and Innovative Technologies, University of Economics and Innovation in Lublin, 20-209 Lublin, PolandInstitute of Computer Science and Innovative Technologies, University of Economics and Innovation in Lublin, 20-209 Lublin, PolandThis paper describes the method developed using the Extreme Gradient Boosting (Xgboost) algorithm that allows high-resolution imaging using the ultrasound tomography (UST) signal. More precisely, we can locate, isolate, and use the reflective peaks from the UST signal to achieve high-resolution images with low noise, which are far more useful for the location of points where the reflection occurred inside the experimental tank. Each reconstruction is divided into two parts, estimation of starting points of wave packets of raw signal (SAT—starting arrival time) and image reconstruction via XGBoost algorithm based on SAT matrix. This technology is the basis of a project to design non-invasive monitoring and diagnostics of technological processes. In this paper, we present a method of the complete solution for monitoring industrial processes. The measurements used in the study were obtained with the author’s solution of ultrasound tomography.https://www.mdpi.com/1996-1073/14/22/7549ultrasound imaginingmachine learningextreme gradient boosting |
| spellingShingle | Dariusz Majerek Tomasz Rymarczyk Dariusz Wójcik Edward Kozłowski Magda Rzemieniak Janusz Gudowski Konrad Gauda Machine Learning and Deterministic Approach to the Reflective Ultrasound Tomography Energies ultrasound imagining machine learning extreme gradient boosting |
| title | Machine Learning and Deterministic Approach to the Reflective Ultrasound Tomography |
| title_full | Machine Learning and Deterministic Approach to the Reflective Ultrasound Tomography |
| title_fullStr | Machine Learning and Deterministic Approach to the Reflective Ultrasound Tomography |
| title_full_unstemmed | Machine Learning and Deterministic Approach to the Reflective Ultrasound Tomography |
| title_short | Machine Learning and Deterministic Approach to the Reflective Ultrasound Tomography |
| title_sort | machine learning and deterministic approach to the reflective ultrasound tomography |
| topic | ultrasound imagining machine learning extreme gradient boosting |
| url | https://www.mdpi.com/1996-1073/14/22/7549 |
| work_keys_str_mv | AT dariuszmajerek machinelearninganddeterministicapproachtothereflectiveultrasoundtomography AT tomaszrymarczyk machinelearninganddeterministicapproachtothereflectiveultrasoundtomography AT dariuszwojcik machinelearninganddeterministicapproachtothereflectiveultrasoundtomography AT edwardkozłowski machinelearninganddeterministicapproachtothereflectiveultrasoundtomography AT magdarzemieniak machinelearninganddeterministicapproachtothereflectiveultrasoundtomography AT januszgudowski machinelearninganddeterministicapproachtothereflectiveultrasoundtomography AT konradgauda machinelearninganddeterministicapproachtothereflectiveultrasoundtomography |