Dr Conrad Tucker de Penn State University a Centrale Nantes

Le Dr Conrad Tucker, professeur à Penn State University, a donné à l'Ecole Centrale de Nantes une conférence sur le thème : Mining Large Scale Social Network Data For Next Generation Knowledge Discovery

le 16 mai 2014

Biosketch

"Conrad Tucker received his B.S in Mechanical Engineering from Rose-Hulman Institute of Technology in 2004 and his M.S. (Industrial Engineering), MBA (Business Administration) and Ph.D. (Industrial Engineering) from the University of Illinois at Urbana Champaign. His research interests are in formalizing system design processes under the paradigm of knowledge discovery, optimization, data mining, and informatics. His research interests include applications in complex systems design and operation, product portfolio/family design, and sustainable system design optimization in the areas of healthcare, consumer electronics, environment, and national security."
Le Dr Conrad Tucker, accompagne 6 étudiants de Penn State University dans leur séjour à Centrale Nantes.


Abstract:
Society generates more than 2.5 quintillion (10^18) bytes of data each day. A significant amount of this data is generated through mobile and social media services such as Twitter®, Facebook®, and Google® that process anywhere between 12 terabytes (10^12) to 20 petabytes (10^15) of data each day. These online user-propelled networks are now being referred to as digitized word of mouth networks, and have been successful in shaping anything from global politics to financial markets. Engineering Designers (Designers) however still have not been able to successfully leverage large scale data in meaningful ways during the design process, leading to a mismatch between what is designed and what is successful in the marketplace.

The objective of this research is to utilize publicly available social media data to model and predict the characteristics that systems exhibit (ranging from next generation product designs to biological systems such as influenza epidemics). This research is grounded in data mining theory and natural language processing techniques and assesses the veracity of resulting predictive models, based on real life data.
Publié le 16 mai 2014 Mis à jour le 9 février 2020