Logistic Regression for Machine Learning in Process Tomography
The main goal of the research presented in this paper was to develop a refined machine learning algorithm for industrial tomography applications. The article presents algorithms based on logistic regression in relation to image reconstruction using electrical impedance tomography (EIT) and ultrasoun...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/15/3400 |
| _version_ | 1818007513642041344 |
|---|---|
| author | Tomasz Rymarczyk Edward Kozłowski Grzegorz Kłosowski Konrad Niderla |
| author_facet | Tomasz Rymarczyk Edward Kozłowski Grzegorz Kłosowski Konrad Niderla |
| author_sort | Tomasz Rymarczyk |
| collection | DOAJ |
| description | The main goal of the research presented in this paper was to develop a refined machine learning algorithm for industrial tomography applications. The article presents algorithms based on logistic regression in relation to image reconstruction using electrical impedance tomography (EIT) and ultrasound transmission tomography (UST). The test object was a tank filled with water in which reconstructed objects were placed. For both EIT and UST, a novel approach was used in which each pixel of the output image was reconstructed by a separately trained prediction system. Therefore, it was necessary to use many predictive systems whose number corresponds to the number of pixels of the output image. Thanks to this approach the under-completed problem was changed to an over-completed one. To reduce the number of predictors in logistic regression by removing irrelevant and mutually correlated entries, the elastic net method was used. The developed algorithm that reconstructs images pixel-by-pixel is insensitive to the shape, number and position of the reconstructed objects. In order to assess the quality of mappings obtained thanks to the new algorithm, appropriate metrics were used: compatibility ratio (CR) and relative error (RE). The obtained results enabled the assessment of the usefulness of logistic regression in the reconstruction of EIT and UST images. |
| first_indexed | 2024-04-14T05:16:28Z |
| format | Article |
| id | doaj.art-76aac811724d4a529d7dc4ebabacdec8 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T05:16:28Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-76aac811724d4a529d7dc4ebabacdec82022-12-22T02:10:21ZengMDPI AGSensors1424-82202019-08-011915340010.3390/s19153400s19153400Logistic Regression for Machine Learning in Process TomographyTomasz Rymarczyk0Edward Kozłowski1Grzegorz Kłosowski2Konrad Niderla3Research & Development Centre Netrix S.A., University of Economics and Innovation in Lublin, 20-209 Lublin, PolandFaculty of Management, Lublin University of Technology, 20-618 Lublin, PolandFaculty of Management, Lublin University of Technology, 20-618 Lublin, PolandResearch & Development Centre Netrix S.A., University of Economics and Innovation in Lublin, 20-209 Lublin, PolandThe main goal of the research presented in this paper was to develop a refined machine learning algorithm for industrial tomography applications. The article presents algorithms based on logistic regression in relation to image reconstruction using electrical impedance tomography (EIT) and ultrasound transmission tomography (UST). The test object was a tank filled with water in which reconstructed objects were placed. For both EIT and UST, a novel approach was used in which each pixel of the output image was reconstructed by a separately trained prediction system. Therefore, it was necessary to use many predictive systems whose number corresponds to the number of pixels of the output image. Thanks to this approach the under-completed problem was changed to an over-completed one. To reduce the number of predictors in logistic regression by removing irrelevant and mutually correlated entries, the elastic net method was used. The developed algorithm that reconstructs images pixel-by-pixel is insensitive to the shape, number and position of the reconstructed objects. In order to assess the quality of mappings obtained thanks to the new algorithm, appropriate metrics were used: compatibility ratio (CR) and relative error (RE). The obtained results enabled the assessment of the usefulness of logistic regression in the reconstruction of EIT and UST images.https://www.mdpi.com/1424-8220/19/15/3400machine learningelectrical impedance tomographyultrasound tomographyprocess tomographyimage reconstruction |
| spellingShingle | Tomasz Rymarczyk Edward Kozłowski Grzegorz Kłosowski Konrad Niderla Logistic Regression for Machine Learning in Process Tomography Sensors machine learning electrical impedance tomography ultrasound tomography process tomography image reconstruction |
| title | Logistic Regression for Machine Learning in Process Tomography |
| title_full | Logistic Regression for Machine Learning in Process Tomography |
| title_fullStr | Logistic Regression for Machine Learning in Process Tomography |
| title_full_unstemmed | Logistic Regression for Machine Learning in Process Tomography |
| title_short | Logistic Regression for Machine Learning in Process Tomography |
| title_sort | logistic regression for machine learning in process tomography |
| topic | machine learning electrical impedance tomography ultrasound tomography process tomography image reconstruction |
| url | https://www.mdpi.com/1424-8220/19/15/3400 |
| work_keys_str_mv | AT tomaszrymarczyk logisticregressionformachinelearninginprocesstomography AT edwardkozłowski logisticregressionformachinelearninginprocesstomography AT grzegorzkłosowski logisticregressionformachinelearninginprocesstomography AT konradniderla logisticregressionformachinelearninginprocesstomography |