Neural networks and PCA principal component methods application to compress the results of the construction object’s displacement

openaccess, Vol. 603 (11) 2022 / poniedziałek, 28 listopada, 2022

(Open Access)

DOI: 10.15199/33.2022.11.05

Mrówczyńska Maria. 2022. Neural networks and PCA principal component methods application to compress the results of the construction object’s displacement. Volume 603. Issue 11. Pages 16-18. Article in PDF file

Accepted for publication: 03.10.2022 r.

The article proposes using the PCA (Principal Component Analysis) transformation method carried out using a neural network to compressmultidimensional data obtained from geodeticmeasurements.As an example of the possibility of using the presented approach, the results of measurements of vertical displacements of a construction object were used. Tests to assess the effectiveness of the proposed method were performed using a correlation coefficient and a mean-square error that did not exceed twice the error of the average measurement. The results of numerical analyses were compared with the values of vertical displacements of the measuring and control network points obtained from actual measurements. The results suggest that the approach can be applied to the compression and subsequent reconstruction of geodetic monitoring data without compromising the accuracy of displacement identification.
  1. Yanga DH et al. Monitoring and analysis of thermal efect on tower displacement in cable- -stayed bridge. Measurement. 2018; https://doi. org/10.1016/j. measurement. 2017.10.036.
  2. Nowogońska B. Konsekwencje błędnych decyzji remontowych w XVII-wiecznym budynku szkieletowym. Materiały Budowlane. 2021; 10.15199/33.2021.10.07.
  3.  Błaszczak-Bąk Wet al. Optimization of point clouds for 3D bas-relief modeling. Automation in Construction 2022; 2022.104352.
  4. Skrzypczak I et al. Scan-to-BIM method in construction: assessment of the 3D buildings model accuracy in terms inventorymeasurements. Building Research and Information 2022;
  5. Piniotis G et al. Deck and Cble Dynamic Testing of a Single-span Bridge Using Radar Interferometry and Videometry Measurements, Journal of Applied Geodesy 2016; https://doi. org/10.1515/jag-2015-0030.
  6.  Mrówczyńska et al. compression of results of geodetic displacement measurements using the PCA method and neural networks. Measurement 2020; 2020.107693.
  7.  LiaY et al.Accuracy enhancement of high-rateGNSS positions using a complete ensemble empiricalmode decomposition-basedmultiscalemultiway PCA. Journal ofAsian Earth Sciences 2019; 2018.07.025.
  8.  Wen L et al. Compression of smart meter big data: A survey. Renewable and Sustainable Energy Reviews 2018; rser.2018.03.088.
  9. Mrówczyńska M. Analysis of principal components used for modelling changes in glacitectonically disturbed areas. Journal of Water and Land Development. 2018;
  10.  Wang H, Hong M. Supervised Hebb rule based feature selection for text classification. Information Processing & Management.2018;
dr hab. inż. Maria Mrówczyńska, prof. uczelni, Uniwersytet Zielonogórski, Instytut Budownictwa ORCID: 0000-0002-4762-3999

dr hab. inż. Maria Mrówczyńska, prof. uczelni, Uniwersytet Zielonogórski, Instytut Budownictwa ORCID: 0000-0002-4762-3999

Full paper:

DOI: 10.15199/33.2022.11.05

Article in PDF file