| Popis: |
In this study, the relationship between accident severity and accident measures in the occupational accidents that occurred during the building process was investigated. By using past accident data, an integrated model has been developed which can predict what measures should be taken in future occupational accidents and what the outcome of the accident would be if these measures are not taken. This estimation model was developed by integrating the AHP (Analytical Hierarchy Process) and ANN (Artificial Neural Networks) methods, which are frequently used by researchers, to complement each other at the point where they are weak. The significance of the model was tested with real data by conducting a field study. For the sample, 4 (four) types of occupational accidents that caused the most deaths were selected, and 35 (thirty-five) past accident data were collected for each of these occupational accident types. For AHP method, which weighting the input layer of the ANN method, the binary comparison data was obtained through the survey method from the OHS (Occupational Health and Safety) experts working in the sector by a professional survey firm. From the data obtained, 120 data were used to train network, 20 data were used to test it. As a result, the relationship between risk reducing measures and accident severity was found to be 90% significant, provided that it is limited to the accident data collected. |
