Onur Ilkin Dulgeroglu

Automated Bed Assignments in a Complex and Dynamic Hospital Environment

Bed management, an important function of any hospital, has a major impact on patient care, patient flow, patient and staff satisfaction, and ultimately on the hospitals operating margin. A key challenge in bed management is optimizing the bed-assignment process in a complex and dynamic operating environment. Efficient bed assignment requires the merging of clinical information, hospital operations information, interdependencies between units, and real-time information on patients, resources, and workflows. We have developed analytical decision support tools with embedded mathematical models to periodically recommend bed-patient assignments. Using an innovative mixed-integer goal-programming modeling approach, we are able to accommodate the multiple goals and complex operating rules of different hospitals. We implemented and hosted our prototype bed-assignment solution as a cloud-based application for Mount Sinai Medical Center in New York.

The role of learning on industrial simulation design and analysis

The capability of modeling real-world system operations has turned simulation into an indispensable problem-solving methodology for business system design and analysis. Today, simulation supports decisions ranging from sourcing to operations to finance, starting at the strategic level and proceeding towards tactical and operational levels of decision-making. In such a dynamic setting, the practice of simulation goes beyond being a static problem-solving exercise and requires integration with learning. This article discusses the role of learning in simulation design and analysis motivated by the needs of industrial problems and describes how selected tools of statistical learning can be utilized for this purpose.

Semiconductor manufacturing simulation design and analysis with limited data

This paper discusses simulation design and analysis for Silicon Carbide (SiC) manufacturing operations management at New York Power Electronics Manufacturing Consortium (PEMC) facility. Prior work has addressed the development of manufacturing system simulation as the decision support to solve the strategic equipment portfolio selection problem for the SiC fab design [1]. As we move into the phase of collecting data from the equipment purchased for the PEMC facility, we discuss how to redesign our manufacturing simulations and analyze their outputs to overcome the challenges that naturally arise in the presence of limited fab data. We conclude with insights on how an approach aimed to reflect learning from data can enable our discrete-event stochastic simulation to accurately estimate the performance measures for SiC manufacturing at the PEMC facility.