Smith*, Alice E. (Auburn University)

Alice Smith speaker

Alice E. Smith
Joe W. Forehand/Accenture Distinguished Professor 
Auburn University
Department of Industrial and Systems Engineering
3301 Shelby Center
Auburn, AL 36849 USA

Phone: 334-844-4340


Decision Science Inspired by Nature

This talk will discuss using computational approximations of natural systems for decision science.  These paradigms range in fidelity with their natural systems inspirations but all seek to leverage the structures and operations of nature doing what it does best – novelty detection, system optimization, adaptability to dynamic environments, robustness, and flexibility.  More specifically, the well-known, but often misunderstood and misused, natural system computational paradigms of artificial neural networks and evolutionary algorithms will be considered for use in decision science.  Used judiciously and knowledgeably these approaches can offer significant advantages in diverse decision environments.   A curated selection of diverse applications from the speaker’s more than 20 years of experience in this field will be briefly highlighted.


Blast from the Past – Revisiting Evolutionary Strategies for the Design of Engineered Systems

This plenary will discuss the potential advantages of using one of the most venerable, but currently underutilized, evolutionary computation paradigms, that of Evolutionary Strategies (ES).  Developed some 50 years ago with the aim of improving engineering design, this paradigm has often been overlooked in favor of the more popular paradigms of genetic algorithms, ant colony optimization, particle swarm optimization and others.  However, ES is an appealing combination of simplicity and effectiveness, especially for real valued variables.  This talk will discuss the motivations of and experiences with using ES for three diverse domains in engineering design – aircraft airfoil design, optimal configurations for order picking warehouses, and design of resilient ad hoc wireless communications networks.  These applications integrate the ES with other computational methods including simulation to form comprehensive and pragmatic design tools.  The “Old School” paradigm of   ES has much to offer contemporary users of meta-heuristics and deserves a higher profile within the computational intelligence community.


Predictive Maintenance Using Neural Networks For Airport People Mover Vehicles

This talk describes a case study of the development and testing of a prototype system to support condition-based maintenance of the door systems of airport transportation vehicles. These “people mover” vehicles are found in airports around the world and must meet stringent availability requirements. This has caused over maintenance of the vehicles while still allowing for failures. To address this issue, a predictive maintenance system was developed to monitor the state of the vehicle doors and signal when maintenance is needed. Every door open/close cycle produces a “signature” that can indicate the current degradation level of the door system. A combined statistical and neural network approach was used. Time, electrical current and voltage signals from the open/close cycles are processed in real time to estimate, using the neural network, the condition of the door set relative to maintenance needs. Data collection hardware for the vehicle was designed, developed and tested to monitor door characteristics to quickly predict degraded performance, and to anticipate failures. The benefits anticipated using predictive diagnostics over a scheduled maintenance approach are: 1) more cost effective maintenance because system and/or components are maintained only where and when needed and 2) degradation-type failures and downtime reduced to a minimum because systems and their components can be maintained during an early phase of degradation, long before failure can occur. The prototype system was installed on vehicle door sets at the Pittsburgh International Airport and tested for several months under actual operating conditions. The findings included: 1) the idea of predictive maintenance for degradation-type behavior is technically sound, 2) it is possible to design, build and implement a predictive maintenance system for doors without major design changes and without significant investment, 3) empirical modeling does appear to be practical and effective, and 4) analytic modeling does not appear to be practical and therefore traditional model based approaches will probably fail. This project was joint with Daimler Research in Germany and Adtranz (now, Bombardier) company in Pittsburgh, Pennsylvania. The project resulted in a U.S. patent and several international patents.


Facility Layout for Semiconductor Manufacturing in a Double Row Configuration

Facility layout problems have drawn much attention over the years, as evidenced by many different versions and formulations in the manufacturing context.  This talk will briefly introduce optimal facilities design and then discuss the special aspects of certain environments including microelectronics manufacturing.  Motivated by semiconductor manufacturing, where the floor space is highly expensive (such as in a cleanroom environment) but there is also considerable material handling amongst machines, an approach combining a multi-objective tabu search with linear programming (MTS-LP) is proposed.  This is done for an extended double row layout problem (EDRLP), in which the objective is to determine exact locations of machines in both rows to minimize material handling cost and layout area, where material flows are asymmetric.  First, a formulation of the problem is established then an optimization framework is devised that utilizes MTS-LP to determine a set of non-dominated solutions, both sequences and positions of machines. Finally, the set of Pareto solutions is generated from the non-dominated solutions. Experimental results show that MTS-LP is able to obtain sets of Pareto solutions which are far better than those obtained by CPLEX within reasonable times.


Computational Logistics for Innovative Designs and Operations in Order Picking Warehouses

This talk discusses computational approaches to difficult problems in warehouse design and operations with a focus on order picking warehouses.  The computational framework includes heuristic optimization and stochastic simulation.  Innovations in design are shown which improve operations and are pragmatic to implement.


Education & Background

  • BSCE, Rice University
  • MBA, Saint Louis University
  • PhD, Missouri University of Science and Technology

Alice E. Smith is the Joe W. Forehand/Accenture Distinguished Professor of the Industrial and Systems Engineering Department at Auburn University, where she served as Department Chair from 1999-2011.  She also has a joint appointment with the Department of Computer Science and Software Engineering.  Previously, she was on the faculty of the Department of Industrial Engineering at the University of Pittsburgh from 1991-99, which she joined after industrial experience with Southwestern Bell Corporation.  Dr. Smith has degrees from Rice University, Saint Louis University, and Missouri University of Science and Technology.

Dr. Smith’s research focus is analysis, modeling and optimization of complex systems with emphasis on computation inspired by natural systems.  She holds one U.S. patent and several international patents and has authored more than 200 publications which have garnered over 4,000 citations and an H Index of 27 (ISI Web of Science) and over 11,000 citations and an H Index of 48 (Google Scholar).  Several of her papers are among the most highly cited in their respective journals including the most cited paper of Reliability Engineering & System Safety and the 2nd most cited paper of IEEE Transactions on Reliability.  She won the E. L. Grant Best Paper Awards in 1999 and in 2006, and the William A. J. Golomski Best Paper Award in 2002.  Dr. Smith is the Editor in Chief of INFORMS Journal on Computing and an Area Editor of Computers & Operations Research.

Dr. Smith has been a principal investigator on over $8.5 million of sponsored research with funding by NASA, U.S. Department of Defense, Missile Defense Agency, National Security Agency, NIST, U.S. Department of Transportation, Lockheed Martin, Adtranz (now Bombardier Transportation), the Ben Franklin Technology Center of Western Pennsylvania and U.S. National Science Foundation, from which she has been awarded 17 distinct grants including a CAREER grant in 1995 and an ADVANCE Leadership grant in 2001.  Her industrial partners on sponsored research projects have included DaimlerChrysler Electronics, Toyota, Eljer, Extrude Hone, Ford Motor and Crucible Compaction Metals.  International research collaborations have been sponsored by Germany, Mexico, Japan, Turkey, United Kingdom, The Netherlands, Egypt, South Korea, Iraq, China, Colombia, Chile, Algeria and the U.S., and by the Institute of International Education.  In 2013 she was a Fulbright Senior Scholar at Bilkent University in An  kara, Turkey, in 2016 a Fulbright Specialist at EAFIT in Medellin, Colombia, and in 2017 a Senior Fulbright Fellow at Pontifical Catholic University of Valparaíso, Chile.

For accomplishments in research, education and service she was named the Joe W. Forehand/Accenture Distinguished Professor in 2015.  Previously, she was the H. Allen and Martha Reed Professor.  In 2017, she was awarded the inaugural Auburn University 100 Women Strong Leadership in Diversity Faculty Award.  Dr. Smith was awarded the Wellington Award in 2016, the IIE Albert G. Holzman Distinguished Educator Award in 2012 and the INFORMS WORMS Award for the Advancement of Women in OR/MS in 2009.  Dr. Smith was named the Philpott‐ WestPoint Stevens Professor in 2001, received the Senior Research Award of the College of Engineering at Auburn University in 2001 and the University of Pittsburgh School of Engineering Board of Visitors Faculty Award for Research and Scholarly Activity in 1996. 

Dr. Smith is a fellow of the Institute of Industrial and Systems Engineers (IISE), a fellow of the Institute of Electrical and Electronics Engineers (IEEE) and a senior member of the Society of Women Engineers, a member of Tau Beta Pi and the Institute for Operations Research and Management Science (INFORMS), and a Registered Professional Engineer in Alabama and Pennsylvania.  She was elected to serve on the Administrative Committee of the IEEE Computational Intelligence Society from 2013-18 and as IISE Senior Vice President – Publications from 2014-17.  She served as associate editor for two IEEE journals and is currently an IEEE Computational Intelligence Society Distinguished Lecturer.  She has served as Chair of the Council of Industrial Engineering Academic Department Heads and as President of the INFORMS Association of Chairs of Operations Research Departments.  She is an IEEE CIS Distinguished Lecturer and is a recent keynote speaker at the International INFORMS Conference (2019) and at the IEEE World Congress on Computational Intelligence (2018).