AI-based predictive modeling for safety assessment in construction industry

Download

index.pdf

Date

2019

Author

Ayhan, Bilal Umut

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

307
views

166
downloads

The predictive modeling is a popular research area among the researchers. Most of the proposed models cannot provide a solution for the needs of every contractor as the existing ones served for only a specific task. Therefore, using these systems become inevitably burden on contractors due to its difficulty of use. The thesis aims to provide an AI-based safety assessment strategy for every project. The assessment strategy encapsulated the detection of trends in safety failures and corrective actions to prevent them. The study covered two parts. The first part explained a hybrid model of ANN and Fuzzy Set Theory, based on over 17,000 incident cases. The ANN model achieved to forecast 84% incident within 90% confidence, and integrating the fuzzy inference system increased the prediction performance slightly. The second part introduced the use of LCCA as a Big Data analytics to address the heterogeneity problem. Although the model employed around 5,000 cases for training, the prediction performance was quite similar to the first part. Besides, this part included a comparison of CBR and ANN to reveal which approach demonstrated better compliance with the incident data. Results exhibited the inclusion of big data analytic improved the prediction performance despite a significant decrease in sample size. The study advanced with the fatal accident analysis to promote prevention measures. Measures offered attribute-based corrections by examining the relationships between the attributes. Ultimately, the proposed methodology can aid construction industry professionals in analyzing prospective safety problems using the large-scale collected data during the construction.

Subject Keywords

Artificial intelligence., Predictive Modeling, Case-Base Reasoning, Artificial Neural Networks, Accident Prevention.

URI

http://etd.lib.metu.edu.tr/upload/12624797/index.pdf
https://hdl.handle.net/11511/45051

Collections

Graduate School of Natural and Applied Sciences, Thesis

Suggestions

OpenMETU
Core

A New Mathematical Approach in Environmental and Life Sciences: Gene-Environment Networks and Their Dynamics Weber, Gerhard Wilhelm; Alparslan-Gok, S. Z.; Soyler, B. (Springer Science and Business Media LLC, 2009-04-01) An important research area in life sciences is devoted to modeling, prediction, and dynamics of gene-expression patterns. As clearly understood in these days, this enterprise cannot become satisfactory without acknowledging the role of the environment. To a representation of past, present, and most likely future states, we also encounter measurement errors and uncertainties. This paper surveys and improves recent advances in understanding the foundations and interdisciplinary implications of the newly intro...
Deep learning approach for laboratory mice grimace scaling Eral, Mustafa; Halıcı, Uğur; Department of Electrical and Electronics Engineering (2016) Deep learning is extremely attractive research topic in pattern recognition and machine learning areas. Applications in speech recognition, natural language processing, and machine vision fields gained huge acceleration in performance by employing deep learning. In this thesis, deep learning is used for medical purposes in order to scale pain degree of drug stimulated mice by examining facial grimace. For this purpose each frame in the videos in the training set were scaled manually by experts according to ...
Uncertainty models for vector based functional curves and assessing the reliability of G-Band Kurtar, Ahmet Kürşat; Düzgün, H. Şebnem; Department of Geodetic and Geographical Information Technologies (2006) This study is about uncertainty medelling for vector features in geographic information systems (GIS). It has mainly two objectives which are about the band models used for uncertainty modelling . The first one is the assessment of accuracy of GBand model, which is the latest and the most complex uncertainty handling model for vector features. Some simulations and tests are applied to test the reliability of accuracy of G-Band with comparing Chrisman’s epsilon band model, which is the most frequently used b...
Artificial-neural-network prediction of hexagonal lattice parameters for non-stoichiometric apatites Kockan, Umit; Ozturk, Fahrettin; Evis, Zafer (2014-01-01) In this study, hexagonal lattice parameters (a and c) and unit-cell volumes of non-stoichiometric apatites of M-10(TO4)(6)X-2 are predicted from their ionic radii with artificial neural networks. A multilayer-perceptron network is used for training. The results indicate that the Bayesian regularization method with four neurons in the hidden layer with a tansig activation function and one neuron in the output layer with a purelin function gives the best results. It is found that the errors for the predicted ...
PROGRESSIVE CLUSTERING OF MANIFOLD-MODELED DATA BASED ON TANGENT SPACE VARIATIONS Gokdogan, Gokhan; Vural, Elif (2017-09-28) An important research topic of the recent years has been to understand and analyze manifold-modeled data for clustering and classification applications. Most clustering methods developed for data of non-linear and low-dimensional structure are based on local linearity assumptions. However, clustering algorithms based on locally linear representations can tolerate difficult sampling conditions only to some extent, and may fail for scarcely sampled data manifolds or at high-curvature regions. In this paper, w...

Citation Formats

B. U. Ayhan, “AI-based predictive modeling for safety assessment in construction industry,” Thesis (M.S.) -- Graduate School of Natural and Applied Sciences. Civil Engineering., Middle East Technical University, 2019.