Home C.V. Research Publications Teaching Evaluations Links Syllabi Dr. Durai Sundaramoorthi
Research
    
   
Dr. Durai Sundaramoorthi's current research focuses on Simulation Modeling and Optimization of Stochastic Systems (SIMMOSS). Most of the systems in the real world are too complex and uncertain to use traditional math modeling approaches for analysis. In such situations, simulation modeling is a good choice for analyzing, evaluating and optimizing the system. Availability of RFID and other latest technologies have enabled data collection from complex systems and utilization of data-integrated techniques for simulation. His primary expertise is in using tree-based data mining techniques to simulate Markovian-type stochastic in the system. In traditional stochastic simulation models, transition probabilities are obtained either subjectively or by looking at all of the possible combinations of the levels of the simulation state variables. If the system under consideration is complex, then a subjective approach is unlikely to be accurate, and an approach using all of the possible combinations of the states will be impractical. For instance, six categorical variables with ten categories each will lead to a million possible states in the simulation. Obtaining accurate transition probabilities for such a huge simulation model is difficult. In his research, using data from Baylor Regional Medical Center (Baylor) in Grapevine, Texas, Dr. Durai introduced a new methodology to reduce the number of combinations of the simulation state variables and find transition probabilities for stochastic simulation models. Simulation models developed with this approach will be much more representative of the actual system and more efficient than those that consider all of the possible combinations.