A NN-Based Approach for Monitoring Early Warnings of Risk in Historic Buildings via Image Novelty Detection

Abstract:

Architectural heritage is an important part of the history and identity of countries, but ancient buildings suffer a high vulnerability to hazards, which may induce unpredictable damages. For this purpose, the development of techniques for monitoring historic buildings and immediately alerting in case of early vulnerability assessment is a main objective to be pursued. This paper concerns with a proposal of noninvasive Neural Network-based approach for predicting risk events in artistic buildings. More in detail, a neural approach is suggested for detecting temporal novelties in images of historic evidences with the aim of monitoring early warning of risk events.

• Periodical: Key Engineering Materials (Volume 628)
• Pages: 212-217
• DOI: https://doi.org/10.4028/www.scientific.net/KEM.628.212
• Online since: August 2014
• Authors: Leonarda Carnimeo*, Rosamaria Nitti
• Keywords: Historic Buildings, Image Processing Techniques, Neural Network (NN), Risk Prevention, Sensor-Based Monitoring Systems

References

[1] S. Mastrodicasa, Dissesti statici delle Strutture Edilizie, seventh ed., Hoepli, Milan, (1983).

[2] M. Lepidi, V. Gattulli, D. Foti, Swinging-bell Resonances and their Cancellation Identified by Dynamical Testing in a Modern Bell Tower, Engineering Structures, 31 (2009), 1486-1500, ISSN: 0141-0296.

DOI: 10.1016/j.engstruct.2009.02.014

[3] D. Foti, S. Ivorra, M. F. Sabbà, Dynamic Investigation of an Ancient Bell Tower with Operational Modal Analysis, The Open Construction and Building Technology Journal, 6, (2012) 384-391, ISSN 1874-8368.

DOI: 10.2174/1874836801206010384

[4] D. Foti, Dynamic identification techniques to numerically detect the structural damage, The Open Construction and Building Technology Journal, 7 (2013) 43-50, ISSN 1874-8368.

DOI: 10.2174/1874836801307010043

[5] D. Foti, V. Gattulli, F. Potenza, Output-only identification and model updating by dynamic testing in unfavorable conditions of a seismically damaged building, Computer-Aided Civil and Infrastructure Engineering, 2 (2014), Online ISSN: 1467-8667.

DOI: 10.1111/mice.12071

[6] Council of Europe Recommendation of 1993, On the Protection of the Architectural Heritage against natural disasters, (1993).

[7] A. Menuge, Understanding Historic Buildings, ed. English Heritage, (2006).

[8] K. Tugce, G. Murat, B. Selcen, Artificial Neural Network to Predict Daylight Illuminance in Office Building, Building and Environment, 44(8) (2009) 1751-1757.

DOI: 10.1016/j.buildenv.2008.11.012

[9] N. Sriram, S. Suresh, N. Sundararajan, Direct Adaptive Neural Controller for Earthquake Excited Nonlinear Base Isolated Buildings, 22nd IEEE Int. Sym. on Intelligent Control, Singapore, (2007) 138-143.

DOI: 10.1109/isic.2007.4450874

[10] C. Jing, Z. Qingjie, S. Youpo, Predictive Model of Artificial Neural Network for Disaster Prevention. 2nd IEEE Int. Conf. on Information Management and Engineering (ICIME). Chengdu, China, (2010) 365-369.

[11] J. Wang, H. Gao, J. Xi, Application of Artificial Neural Network and GIS in Urban Earthquake Disaster Mitigation. Int. Conf. on Intelligent Computation Technology and Automation (ICICTA). Changsha, Hunan, China, 1 (2010) 726-729.

DOI: 10.1109/icicta.2010.409

[12] L. Carnimeo, A. Giaquinto, Cellular Neural Networks for Obstacle Detection in Stereo Vision Imagery, Cellular Neural Networks: Theory and Appl., I(8), New York, Nova Science Publishers, (2004), 173-180.

[13] XJ. Chen, ZF Gao, W. Wang, Application of BP Artificial Neural Network in Structure Damage Identification, Int. Conf. on Intelligent Computation Technology and Automation (ICICTA), Changsha, Hunan, China, 1 (2010) 733-737.

DOI: 10.1109/icicta.2010.150