A new generation of preventive measures of occupational accidents with machine learning
Machine learning can facilitate analysis of causes behind work accidents and incidents. Accidents at work are an unsolved problem in the construction industry. The aim of the project is to develop a prototype of such a machine learning analysis system. The system's effect can be better prevention and higher productivity.
The project is carried out within the framework of a licentiate project in a collaboration between NCC, Chalmers and Mälardalen University.
A current study of practice regarding registration of occupational accidents and incidents is carried out to build up knowledge about the area in which machine learning is to be implemented. Data from a work accident database within NCC is collected and validated. Several different machine learning algorithms are tested on the material and the best combination of algorithms (those that best anticipate accidents) are compiled in a prototype which is then tested by NCC's safety officers. The project's results are communicated in a licentiate dissertation, international articles, conference papers, and articles in Swedish professional journals.
This page is only available in english
- Development Fund of the Swedish Construction Industry (SBUF) (Non Profit, Sweden)