Modeling and Data Analytics

Modeling is the science and art of generating a physical, conceptual or mathematical representation of a system, phenomenon, or device that is difficult to observe directly.

This helps us explain or predict the behavior of physical or abstract systems and is fundamental in physics, ecology, chemistry and earth science, but also now in business and humanities.

For example, electrical engineers use numerical models to solve Maxwell’s Equations for specific structures based on their geometry and material properties. Mechanical or chemical engineers use numerical modeling techniques to solve kinetic, force, or heat diffusion problems based on geometry and physical characteristic.

Numerical and other modeling techniques are universal; their specific application depends on the system or device.

Data Analytics is the art and science of studying random data measured by a sensor or a system of sensors using traditional or innovative techniques with the goal of discovering systemic behaviors that lead to modeling of the system, calculating parameters that characterize our system, categorize and/or predict future behavior of the system.

Traditional data analytics methods include higher-order statistics, convolution and spectral analysis techniques to examine the response of the system to specific or unknown stimuli. This can be used to characterize the stimulus (with a priori knowledge of the system) or the system (with a priori knowledge of the stimulus) or a combination of these. Newer data analytics techniques such as AI, are uniquely appropriate for large data sets gathered from complex systems, and are used for categorization of a system or prediction of its behavior, but are not currently used for parametrization of the physical characteristics of the system.

Cross-functional opportunities:

• Applied mathematics
• Life Sciences
• Animation/Visualization

Interested? Contact Prof. Filippas (avfilippas@vcu.edu)