iconicon Uproszczony widok
 

The Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance Tomography

cris.lastimport.scopus2024-09-18T01:31:14Z
dc.abstract.enThis 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.
dc.affiliationTransportu i Informatyki
dc.contributor.authorGrzegorz Kłosowski
dc.contributor.authorAnna Hoła
dc.contributor.authorTomasz Rymarczyk
dc.contributor.authorŁukasz Skowron
dc.contributor.authorTomasz Wołowiec
dc.contributor.authorMarcin Kowalski
dc.date.accessioned2024-05-10T08:12:53Z
dc.date.available2024-05-10T08:12:53Z
dc.date.issued2021
dc.identifier.doi10.3390/en14227617
dc.identifier.issn1996-1073
dc.identifier.urihttps://repo.akademiawsei.eu/handle/item/319
dc.languageen
dc.pbn.affiliationinformation and communication technology
dc.relation.ispartofEnergies
dc.rightsCC-BY
dc.subject.enelectrical tomography
dc.subject.enmoisture detection
dc.subject.enmachine learning
dc.subject.enneural networks
dc.subject.enlong short-term memory (LSTM)
dc.titleThe Concept of Using LSTM to Detect Moisture in Brick Walls by Means of Electrical Impedance Tomography
dc.typeReviewArticle
dspace.entity.typePublication
oaire.citation.issue22
oaire.citation.volume14