Title:

Data Trend Mining for Predictive Systems Design

Speaker:

Mr. Conrad Tucker

Affiliation:

University of Illinois, Urbana-Champaign, IL

When:

Tuesday, March 15, 2011 at 11:00:00 AM   Add to Calendar

Where:

MRDC Building, Room 4211

Host:

Dr. David Rosen
david.rosen@me.gatech.edu
404-894-9668

Abstract

The focus of this research is to develop a Multidisciplinary Design Optimization (MDO) approach to product design by creating a synergistic methodology that incorporates the objectives of each discipline (engineering design, manufacturing, distribution, etc.) into the realization of an optimal product portfolio. With the incorporation of predictive data mining/machine learning techniques, this research merges customer preferences directly with engineering design to achieve the most sustainable product portfolio. This process is an iterative approach that employs the decomposition and integration techniques of multilevel optimization. The Preference Trend Mining (PTM) algorithm that is proposed in this work aims to address some fundamental challenges of current engineering product modeling techniques by capturing changes in product preferences over time. This enables design engineers to anticipate next generation product features before they become mainstream/unimportant.

Biography

Conrad Tucker received his doctorate degree from the department of Industrial and Enterprise Systems Engineering at the University of Illinois at Urbana-Champaign in December, 2010. He received his B.S. in Mechanical Engineering from Rose-Hulman Institute of Technology in 2004 and an M.S. in Industrial and Systems Engineering from the University of Illinois at Urbana-Champaign in 2007. In May 2009, Conrad was awarded an MBA from the University of Illinois which has complemented his graduate engineering degrees by expanding his network of collaborators and researchers, hereby bringing a different perspective to help address complex engineering design problems. Conrad’s doctoral research, directed by Dr. Harrison Kim has focused on data mining and machine learning in the context of systems design optimization. His dissertation, entitled “Data Trend Mining for Predictive Systems Design” addresses many aspects of systems design and has expanded to include research collaborations with Sandia National Laboratories involving their Future Combat Systems (FCS) analysis models. During his studies as a graduate student, Conrad has had the unique opportunity of collaborating with researchers on the international stage, including a 3-month National Science Foundation research program in Japan, and international academic courses at the University of Warsaw, Poland and Freie University, Germany. In addition to research, Conrad has been equally devoted to teaching and mentoring students at the University of Illinois. For the past 4 years, he has mentored students in the highly competitive Intel Scholars Undergraduate Research program where undergraduates engage in a 2-3 semester long research project. Conrad is part of the inaugural class of the Gates Millennium Scholars (GMS) program (funded by a $1 Billion grant from the Bill and Melinda Gates Foundation) and remains active in the program through volunteer and mentoring efforts.