Design and implementation of advanced Bayesian networks with comparative probability

The main purpose of this research is to enhance the current procedures of designing decision support systems (DSSs) used by decision-makers to comprehend the current situation better in cases where the available amount of information required to make an informed decision is limited. It has been suggested that the highest level of situation awareness can be achieved by a thorough grasp of particular key elements that, if put together, will synthesize the current status of an environment. However, there are many cases where a decision-maker needs to make a decision when no information is available, the source of information is questionable, or the information has yet to arrive. On the other hand, in timely critical decision-making, the availability of information might become a curse rather than a blessing, as the more information is available the more time is required to process it. In time critical situations, time is an expensive commodity not always affordable. For instance, consider a surgeon performing cardiac surgery. With all the new advances in monitoring equipment and medical laboratory tests, there would be too much information to account for before the surgeon could decide on his next “cut”. A DSS could help reduce the amount of information by converting it into the bigger picture through summarizing. The research resulted in a new innovated theory that combines the philosophical comparative approach to probability, the frequency interpretation of probability, dynamic Bayesian networks and the expected utility theory. It enables engineers to write self-learning algorithms that use example of behaviours to model situations, evaluate and make decisions, diagnose problems, and/or find the most probable consequences in real-time. The new theory was particularly applied to the problems of validating equipment readings in an aircraft, flight data analysis, prediction of passengers behaviours, and real-time monitoring and prediction of patients’ states in intensive care units (ICU). The algorithm was able to pinpoint the faulty equipment from between a group of equipment giving false fault indications, an important improvement over the current fault detection procedures. In addition, the network was able to give to the aircraft pilot recommendations about the optimal speed and altitude that will result in reducing fuel consumptions and thereby saving costs and extending equipment lives. On the ICU application side, the algorithm was able to predict those patients with high mortality risk about 24 hours before they actually deceased. In addition, the network can guide nurses to best practices, and to summarize patients’ current state in terms of an overall index. Furthermore, it can use data collected by hospitals to improve its accuracy and to diagnose patients in real-time and predict their state well-ahead to the future