Assessment of Barriers and Drivers to the Adoption of Machine Learning Technologies in Road Construction Site Accident Prevention

The construction industry is fraught with danger. The investigation of the causes of occupational accidents receives considerable attention. Despite the introduction of numerous safety preventive measures in recent decades, occupational safety in the construction industry still requires improvement and progress. Therefore, this study assesses the barriers and drivers to the adoption of Machine Learning (ML) technologies in road construction site accident prevention in Abuja with a view to reducing the rate of accidents in road construction projects. This study used the mixed-methods approach, which involves a combination of both quantitative and qualitative research approaches. In view of this, this study adopted a structured questionnaire and interview schedule to collect data. The use of stratified random and purposive sampling techniques was adopted. A structured questionnaire and interview schedule were adopted to collect data. The analysis of the data was undertaken with the use of descriptive statistics such as content analysis/percentage, frequency counts, and the mean item score (MIS). Results of the analysis revealed that the most significant driver for the adoption of ML technologies in road construction site accident prevention is “efficient construction time and work speed” (MIS = 4.28). Findings from the study show that the most severe barrier to the adoption of ML technologies in road construction site accident prevention is “decision to use differs from client requirements” (MIS = 4.37). The study therefore concludes that the level of readiness for adoption of ML technologies for accident prevention in road construction projects in Abuja is very high but requires improvement by taking cognizance of specific drivers and barriers to continuously have a reduction in the rate of accidents in road construction projects. The study recommends that road construction firms should put up proactive measures to prevent the occurrence of barriers to the adoption of ML technologies, especially with regards to the barrier of “decision to use differs from client requirements,” among other barriers.