The Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance Tomography
This paper refers to an original concept of tomographic measurement of brick wall humidity using an algorithm based on long short-term memory (LSTM) neural networks. The measurement vector was treated as a data sequence with a single time step in the presented study. This approach enabled the use of...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Energies |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1996-1073/14/22/7617 |
| _version_ | 1797510549352742912 |
|---|---|
| author | Grzegorz Kłosowski Anna Hoła Tomasz Rymarczyk Łukasz Skowron Tomasz Wołowiec Marcin Kowalski |
| author_facet | Grzegorz Kłosowski Anna Hoła Tomasz Rymarczyk Łukasz Skowron Tomasz Wołowiec Marcin Kowalski |
| author_sort | Grzegorz Kłosowski |
| collection | DOAJ |
| description | This paper refers to an original concept of tomographic measurement of brick wall humidity using an algorithm based on long short-term memory (LSTM) neural networks. The measurement vector was treated as a data sequence with a single time step in the presented study. This approach enabled the use of an algorithm utilising a recurrent deep neural network of the LSTM type as a system for converting the measurement vector into output images. A prototype electrical impedance tomograph was used in the research. The LSTM network, which is often employed for time series classification, was used to tackle the inverse problem. The task of the LSTM network was to convert 448 voltage measurements into spatial images of a selected section of a historical building’s brick wall. The 3D tomographic image mesh consisted of 11,297 finite elements. A novelty is using the measurement vector as a single time step sequence consisting of 448 features (channels). Through the appropriate selection of network parameters and the training algorithm, it was possible to obtain an LSTM network that reconstructs images of damp brick walls with high accuracy. Additionally, the reconstruction times are very short. |
| first_indexed | 2024-03-10T05:32:58Z |
| format | Article |
| id | doaj.art-ead541ecd1414d3bb57bd0db98969f67 |
| institution | Directory Open Access Journal |
| issn | 1996-1073 |
| language | English |
| last_indexed | 2024-03-10T05:32:58Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Energies |
| spelling | doaj.art-ead541ecd1414d3bb57bd0db98969f672023-11-22T23:10:56ZengMDPI AGEnergies1996-10732021-11-011422761710.3390/en14227617The Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance TomographyGrzegorz Kłosowski0Anna Hoła1Tomasz Rymarczyk2Łukasz Skowron3Tomasz Wołowiec4Marcin Kowalski5Faculty of Management, Lublin University of Technology, 20-618 Lublin, PolandFaculty of Civil Engineering, Wrocław University of Science and Technology, 50-370 Wrocław, PolandFaculty of Transport and Computer Science, University of Economics and Innovation in Lublin, 20-209 Lublin, PolandFaculty of Management, Lublin University of Technology, 20-618 Lublin, PolandInstitute of Public Administration and Business, University of Economics and Innovation in Lublin, 20-209 Lublin, PolandFaculty of Transport and Computer Science, University of Economics and Innovation in Lublin, 20-209 Lublin, PolandThis paper refers to an original concept of tomographic measurement of brick wall humidity using an algorithm based on long short-term memory (LSTM) neural networks. The measurement vector was treated as a data sequence with a single time step in the presented study. This approach enabled the use of an algorithm utilising a recurrent deep neural network of the LSTM type as a system for converting the measurement vector into output images. A prototype electrical impedance tomograph was used in the research. The LSTM network, which is often employed for time series classification, was used to tackle the inverse problem. The task of the LSTM network was to convert 448 voltage measurements into spatial images of a selected section of a historical building’s brick wall. The 3D tomographic image mesh consisted of 11,297 finite elements. A novelty is using the measurement vector as a single time step sequence consisting of 448 features (channels). Through the appropriate selection of network parameters and the training algorithm, it was possible to obtain an LSTM network that reconstructs images of damp brick walls with high accuracy. Additionally, the reconstruction times are very short.https://www.mdpi.com/1996-1073/14/22/7617electrical tomographymoisture detectionmachine learningneural networkslong short-term memory (LSTM) |
| spellingShingle | Grzegorz Kłosowski Anna Hoła Tomasz Rymarczyk Łukasz Skowron Tomasz Wołowiec Marcin Kowalski The Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance Tomography Energies electrical tomography moisture detection machine learning neural networks long short-term memory (LSTM) |
| title | The Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance Tomography |
| title_full | The Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance Tomography |
| title_fullStr | The Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance Tomography |
| title_full_unstemmed | The Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance Tomography |
| title_short | The Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance Tomography |
| title_sort | concept of using lstm to detect moisture in brick walls by means of electrical impedance tomography |
| topic | electrical tomography moisture detection machine learning neural networks long short-term memory (LSTM) |
| url | https://www.mdpi.com/1996-1073/14/22/7617 |
| work_keys_str_mv | AT grzegorzkłosowski theconceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography AT annahoła theconceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography AT tomaszrymarczyk theconceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography AT łukaszskowron theconceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography AT tomaszwołowiec theconceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography AT marcinkowalski theconceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography AT grzegorzkłosowski conceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography AT annahoła conceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography AT tomaszrymarczyk conceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography AT łukaszskowron conceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography AT tomaszwołowiec conceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography AT marcinkowalski conceptofusinglstmtodetectmoistureinbrickwallsbymeansofelectricalimpedancetomography |