Safety is a primary concern of both workers and their employers in most shiftworking situations, particularly in transport operations and the nuclear power or chemical industries where there may be a high “public” or “environmental” risk. A number of authors have noted that many of the “headline hitting” disasters of the last few decades, such as Three Mile Island, Chernobyl, Bhopal, Exxon Valdez, and the Estonia ferry, have all occurred in the early hours of the morning. Further, investigations of these disasters have concluded that they were, at least partially, attributable to fatigue and/or human error. Thus individuals who regularly work on abnormal and/or irregular work schedules are more prone to fatigue than typical day workers. This is due in large part to restricted opportunities for rest, recovery and sleep which may impact on their performance at work and the likelihood of them making a mistake, possibly resulting in an accident. Prolonged exposure to excessive fatigue and sleep deprivation may also impact on the individual’s physical and psychological well-being. Many of the fatigue related problems that shift workers encounter stem from their disrupted biological rhythms. These rhythms have evolved in response to the periodic changes in the environment, such as the day-night cycle. They have become internalized such that the body adjusts many of our physiological and psycho-physiological processes and these regular cyclical changes are known as circadian rhythms (from the Latin ‘about a day’). They are jointly controlled by an internal, or ‘endogenous’, body clock and by external, or ‘exogenous’, factors in the environment such as awareness of clock time, meal timings, social activity, etc. Many authors have developed monitoring devices of one form or another to judge when an individual is at risk due to fatigue. However, at best, these devices can only tell when an individual is at risk, they cannot predict when an individual will be at risk. In contrast, other authors have developed mathematical models based on the averaged data from large groups of individuals that can successfully predict the groups future risk of being fatigued. However, individuals within the group may differ substantially from one another in this respect. Our primary focus is a system that can monitor the fatigue-related changes in each individual and then uses the results of this monitoring to maximize the fit of the model to that individual in an iterative manner. Our aim is to be able to warn individuals that they are likely to become at risk due to fatigue several hours in advance, thus allowing them to plan when and where to take a break.