A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Prediction of Safety Climate through a Neural Network
Safety climate is one of the indicators of safety performance of a construction project. It is a "snapshot" of the safety culture of any organization, and it is dynamic in nature. It reflects the employees' perceptions and attitudes toward the existing safety condition at the construction sites. The important constructs for the safety climate are determined through literature review. The constructs are assumed to influence the behavior of workers at the projects. The aim of this study is to develop a model to predict the safety climate on a construction project using an artificial neural network (ANN). The constructs are used as inputs, and safety climate of a project is used as output for the ANN algorithm. For the study, 200 responses were collected through a questionnaire survey across the country. A three-layer feed forward back propagation neural network (10-18-1) has been found suitable for the analysis. It has been trained, validated, and tested during the model development. The developed model is found to be predicting the safe climate of a construction project reasonably well. Commitment, supervisory environment, personnel appreciation, and competence could be proposed as effective and positive constructs of safety climate based on the results of the study. The model should prove to be helpful to clients and contractors to develop positive safety climates and thereby manage safety of workers effectively at construction projects.
Prediction of Safety Climate through a Neural Network
Safety climate is one of the indicators of safety performance of a construction project. It is a "snapshot" of the safety culture of any organization, and it is dynamic in nature. It reflects the employees' perceptions and attitudes toward the existing safety condition at the construction sites. The important constructs for the safety climate are determined through literature review. The constructs are assumed to influence the behavior of workers at the projects. The aim of this study is to develop a model to predict the safety climate on a construction project using an artificial neural network (ANN). The constructs are used as inputs, and safety climate of a project is used as output for the ANN algorithm. For the study, 200 responses were collected through a questionnaire survey across the country. A three-layer feed forward back propagation neural network (10-18-1) has been found suitable for the analysis. It has been trained, validated, and tested during the model development. The developed model is found to be predicting the safe climate of a construction project reasonably well. Commitment, supervisory environment, personnel appreciation, and competence could be proposed as effective and positive constructs of safety climate based on the results of the study. The model should prove to be helpful to clients and contractors to develop positive safety climates and thereby manage safety of workers effectively at construction projects.
Prediction of Safety Climate through a Neural Network
Patel, D. A. (author) / Jha, K. N. (author)
Construction Research Congress 2014 ; 2014 ; Atlanta, Georgia
Construction Research Congress 2014 ; 1861-1870
2014-05-13
Conference paper
Electronic Resource
English
Neural Network Approach for Safety Climate Prediction
| ASCE | 2014
Neural Network Approach for Safety Climate Prediction
| Online Contents | 2015
Linking Climate Forecasts and Watershed Runoff Prediction Using a Neural Network Approach
| British Library Conference Proceedings | 2005
Linking Climate Forecasts and Watershed Runoff Prediction Using a Neural Network Approach
| British Library Conference Proceedings | 2005