Improved detection of building settlement debris based on deep learning

Cun Wang; Shixuan Han; Jiahao Dou

doi:10.1117/12.3029452

6 May 2024 Improved detection of building settlement debris based on deep learning

Cun Wang, Shixuan Han, Jiahao Dou

Proceedings Volume 13107, Fourth International Conference on Sensors and Information Technology (ICSI 2024); 131071E (2024) https://doi.org/10.1117/12.3029452
Event: Fourth International Conference on Sensors and Information Technology (ICSI 2024), 2024, Xiamen, China

Abstract

In response to the issues of low reliability and poor prediction accuracy in traditional building structure settlement monitoring, a method for building settlement monitoring based on multiple sensors and Radial Basis Function (RBF) neural network is proposed. Building settlement information is collected and wirelessly transmitted using various sensors and hardware devices, including GPRS communication modules. The monitoring data collected by sensors are compared and analyzed to determine the settlement status of the building. An RBF neural network prediction model is constructed for potential settlement points. Additionally, the structural parameters of the RBF neural network are optimized using the leapfrog algorithm. Experimental results demonstrate that this method can accurately assess potential building structure settlements in real-world environments with small prediction errors. The maximum relative error is 4.83%, indicating good predictive capabilities.

(2024) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Cun Wang, Shixuan Han, and Jiahao Dou "Improved detection of building settlement debris based on deep learning", Proc. SPIE 13107, Fourth International Conference on Sensors and Information Technology (ICSI 2024), 131071E (6 May 2024); https://doi.org/10.1117/12.3029452

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available