Modeling Mine Workforce Fatigue: Finding Leading Indicators of Fatigue in Operational Data Sets

Mine workers operate heavy equipment while experiencing varying psychological and physiological impacts caused by fatigue. These vary in scope severity across operators unique mine operations. Previous studies show the impact of fatigue on individuals, raising substantial concerns about safety operation. Unfortunately, data exist to illustrate risks, mechanisms complex pattern contributors are not understood sufficiently, illustrating need for new methods model manage fatigue’s performance safety. Modern technology computational intelligence can provide tools improve practitioners’ understanding workforce Many mines have invested monitoring (PERCLOS, EEG caps, etc.) as a part their health control system. these systems “lagging indicators” and, many instances, only alerts too late worker cycle. Thus, following question arises: other operational leading indicators that managers front-line supervisors use help cope with levels? This paper explores common sets available at most modern how be used The include operational, safety, health, weather data. A machine learning (ML) algorithm is presented tool process issues such ML this study identify potential management make better decisions. Initial findings confirm existing knowledge tying time day hours worked. first generation models future will forthcoming.