The massive amount of data made available by technology advances in different areas, and their huge potential impact on our lives, have opened new doors to systems engineering scientists. However, a rote application of techniques developed in one area to other areas may be rendered completely ineffective if the unique features of these systems were not correctly characterized or fundamental differences were overlooked. Our research is based on the principle that understanding the fundamentals of the system is essential for developing effective data analytics solutions. The central theme of the research program is the theoretical and systematic study of the integration of human learning (e.g., characterization of system unique features, exploitation of system fundamental differences, simplification of the governing chemical/physical principles, etc.) with computationally efficient machine learning and deep learning algorithms for developing hybrid and synergistic human and artificial intelligence based decision-making solutions for various applications.
Research interest: Interface of systems engineering and data analytics.
Application areas: Manufacturing; Biomedical (Speech disorder, Breast Cancer, Prostate Cancer); Healthcare (hospital Operations); Energy (Cellulosic Biofuels, Biogas Conversion); Agriculture (Smart Irrigation, Data-Driven Plant Breeding); Waste to Food, Energy and Water (W2FEW).
Central theme: Integrating systems engineering principles and approaches to data analytics – to address emerging challenges and to dramatically improve performance and effectiveness.