Search
Comparing the Effectiveness of ANNs and SVMs in Forecasting the Impact of Traffic-Induced Vibrations on Building
Abstract
Traffic - induced vibrations may cause damage to structural elements and may even lead to structural collapse. The aim of the article is to compare the effectiveness of algorithms in forecasting the impact of vibrations on buildings using the Machine Learning (ML) methods. The paper presents two alternative approaches by using Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs). Factors that may affect traffic-induced vibrations, such as distance, type of soil, building condition, condition of the road surface and type of the vehicle, were adopted. The analysis was performed according to the standard PN-85 B-02170. The results of both analysed methods are similar. However, after a thorough analysis, it turned out that the SVMs method is more reliable, since more cases were classified correctly. Anyway, the results show that methods of ML might be a good tool to estimate the impact of traffic-induced vibrations on residential buildings.
Citations
-
3
CrossRef
-
0
Web of Science
-
3
Scopus
Authors (3)
Cite as
Full text
full text is not available in portal
Keywords
Details
- Category:
- Conference activity
- Type:
- materiały konferencyjne indeksowane w Web of Science
- Title of issue:
- 2017 Baltic Geodetic Congress (BGC Geomatics) strony 121 - 125
- Language:
- English
- Publication year:
- 2017
- Bibliographic description:
- Jakubczyk-Gałczyńska A., Kristowski A., Jankowski R..: Comparing the Effectiveness of ANNs and SVMs in Forecasting the Impact of Traffic-Induced Vibrations on Building, W: 2017 Baltic Geodetic Congress (BGC Geomatics), 2017, ,.
- DOI:
- Digital Object Identifier (open in new tab) 10.1109/bgc.geomatics.2017.19
- Verified by:
- Gdańsk University of Technology
seen 172 times