<![CDATA[Statistics Seminar::Exploitation and integration of detailed and quick FEA simulations: Improving engineering design via a Bayesian synthesis]]> 27279 This talk is motivated by collaborative work on robust topology design of cellular material at Georgia Tech. In simulating the material properties finite elements analysis (FEA) can be done based on different physical-mechanistic models. Typically a more detailed or accurate model will require longer FEA runs while a simplified or rough model will require quicker FEA runs. They are referred to as detailed and quick simulations respectively. Detailed simulations can take up days of CPU time. While they can provide more accurate results, their number can be limited. On the other hand, many quick simulations can be obtained, though the results are less reliable. A new approach is taken here to combine these sources of data to come up with a meta-model that can be used to describe the relationship between the output of FEA runs (i.e., material properties) and input parameters (i.e., design parameters) and for prediction. Since the quick simulations form the bulk of the data, they are used to build a semi-parametric model based on Gaussian random functions. This fitted model is then

]]> Barbara Christopher 1 1286538132 2010-10-08 11:42:12 1475891575 2016-10-08 01:52:55 0 0 event 2004-01-15T12:00:00-05:00 2004-01-15T00:00:00-05:00 2004-01-15T00:00:00-05:00 2004-01-15 17:00:00 2004-01-15 05:00:00 2004-01-15 05:00:00 2004-01-15T12:00:00-05:00 2004-01-15T00:00:00-05:00 America/New_York America/New_York datetime 2004-01-15 12:00:00 2004-01-15 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[ISyE Faculty Meeting]]> 27279 Dr. Chameau will be our guest speaker.

Please mark this date and time on your calendars.

]]> Barbara Christopher 1 1286538132 2010-10-08 11:42:12 1475891575 2016-10-08 01:52:55 0 0 event 2004-01-20T11:00:00-05:00 2004-01-20T00:00:00-05:00 2004-01-20T00:00:00-05:00 2004-01-20 16:00:00 2004-01-20 05:00:00 2004-01-20 05:00:00 2004-01-20T11:00:00-05:00 2004-01-20T00:00:00-05:00 America/New_York America/New_York datetime 2004-01-20 11:00:00 2004-01-20 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar::On The Relationship Between Bayesian And Frequency Theory Prediction]]> 27279 Given a sufficient statistic, basic predictive inference based on frequency theory actually implies the existence of a prediction distribution function, conditional on the sufficient statistic. Unlike Bayesian posterior predictive functions, the derived distribution is not necessarily a valid one. If it is, the prediction distribution function is necessarily a Bayesian predictive function. In suchcases, the frequency theory prediction method implies a particular Bayesian prior on the nuisance parameter, thus these prediction methods represent a special case of Bayesian predictive inference.

]]> Barbara Christopher 1 1286538131 2010-10-08 11:42:11 1475891575 2016-10-08 01:52:55 0 0 event 2004-01-22T12:00:00-05:00 2004-01-22T00:00:00-05:00 2004-01-22T00:00:00-05:00 2004-01-22 17:00:00 2004-01-22 05:00:00 2004-01-22 05:00:00 2004-01-22T12:00:00-05:00 2004-01-22T00:00:00-05:00 America/New_York America/New_York datetime 2004-01-22 12:00:00 2004-01-22 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar::SPC Procedure for Complicated Functional Data]]> 27279 Functional data characterize quality or reliability performance of many
manufacturing processes. They are very informative in process monitoring
and controlling for nano-machining, ultra-thin semiconductor fabrication,
and antenna, steel-stamping or chemical manufacturing processes as seen in
many literature. In this talk, we present wavelet-based statistical
process control (SPC) procedures and evaluates their performance using
simulation studies. Unlike the recent SPC research on linear profile data
for monitoring global changes of data patterns, our methods focus on local
changes in data segments. In contrast to most of the SPC procedures
developed for detecting a known type of process change, our idea of
updating the selected parameters enables the handling all types of process
changes whether known or unknown. (Joint work with Jye-Chyi Lu).

]]> Barbara Christopher 1 1286538131 2010-10-08 11:42:11 1475891575 2016-10-08 01:52:55 0 0 event 2004-01-29T12:00:00-05:00 2004-01-29T00:00:00-05:00 2004-01-29T00:00:00-05:00 2004-01-29 17:00:00 2004-01-29 05:00:00 2004-01-29 05:00:00 2004-01-29T12:00:00-05:00 2004-01-29T00:00:00-05:00 America/New_York America/New_York datetime 2004-01-29 12:00:00 2004-01-29 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics seminar:: A Review and Analysis of the Mahalanobis-Taguchi System]]> 27279 The Mahalanobos-Taguchi system (MTS) is a relatively new collection of
methods proposed for diagnosis, forecasting, and classification
using multivariate data.
The primary proponent of the MTS is Genichi Taguchi, who is very well
known for his controversial ideas and methods for using design of experiments.
The MTS was claimed to be a groundbreaking new philosophy for multivariate
data analysis and diagnosis and has been popularized in major companies,
such as Ford, GE, Nissan, Sharp, Xerox, etc.
In this talk, we review the methods of the MTS and use a case study based on
medical data to illustrate them. We also compare common classification
tree methods with the MTS in the case study and illustrate the
differences.

]]> Barbara Christopher 1 1286538131 2010-10-08 11:42:11 1475891575 2016-10-08 01:52:55 0 0 event 2004-02-05T12:00:00-05:00 2004-02-05T00:00:00-05:00 2004-02-05T00:00:00-05:00 2004-02-05 17:00:00 2004-02-05 05:00:00 2004-02-05 05:00:00 2004-02-05T12:00:00-05:00 2004-02-05T00:00:00-05:00 America/New_York America/New_York datetime 2004-02-05 12:00:00 2004-02-05 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Natural Systems Seminar: Technological and Natural Systems in the Anthropocene]]> 27279 Brad Allenby is a candidate for the Anderson/Interface Chair in Natural Systems

]]> Barbara Christopher 1 1286538131 2010-10-08 11:42:11 1475891575 2016-10-08 01:52:55 0 0 event 2004-02-12T11:00:00-05:00 2004-02-12T00:00:00-05:00 2004-02-12T00:00:00-05:00 2004-02-12 16:00:00 2004-02-12 05:00:00 2004-02-12 05:00:00 2004-02-12T11:00:00-05:00 2004-02-12T00:00:00-05:00 America/New_York America/New_York datetime 2004-02-12 11:00:00 2004-02-12 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Faculty Candidate Seminar: Statistical Inference for Network Tomography]]> 27279 Abstract: We study network tomography questions, which are large scale inverse
inference problems and vital for many network traffic engineering tasks such as
dynamic routing optimization, Quality of Service (QoS) guarantee. We propose a
pseudo likelihood approach for estimating parameters of these problems based on
the principle of divide-and-conquer. The example of multicast link delay
estimation problem is used to motivate the concept. We then apply the pseudo
likelihood approach to the problem of estimating origin-destination matrix
through link traffic counts, which is one of the core problems in network
traffic engineering.

This is joint work with Bin Yu.

]]> Barbara Christopher 1 1286538130 2010-10-08 11:42:10 1475891575 2016-10-08 01:52:55 0 0 event 2004-02-16T10:00:00-05:00 2004-02-16T00:00:00-05:00 2004-02-16T00:00:00-05:00 2004-02-16 15:00:00 2004-02-16 05:00:00 2004-02-16 05:00:00 2004-02-16T10:00:00-05:00 2004-02-16T00:00:00-05:00 America/New_York America/New_York datetime 2004-02-16 10:00:00 2004-02-16 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Natural Systems Seminar: Dynamic Allocation in Honey Bee and Internet Server Colonies]]> 27279 Craig Tovey is a candidate for the Anderson/Interface Chair in Natural Systems

]]> Barbara Christopher 1 1286538131 2010-10-08 11:42:11 1475891575 2016-10-08 01:52:55 0 0 event 2004-02-17T11:00:00-05:00 2004-02-17T00:00:00-05:00 2004-02-17T00:00:00-05:00 2004-02-17 16:00:00 2004-02-17 05:00:00 2004-02-17 05:00:00 2004-02-17T11:00:00-05:00 2004-02-17T00:00:00-05:00 America/New_York America/New_York datetime 2004-02-17 11:00:00 2004-02-17 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Natural Systems Seminar]]> 27279 Valerie Thomas is a candidate for the Anderson/Interface Chair in Natural Systems

]]> Barbara Christopher 1 1286538131 2010-10-08 11:42:11 1475891575 2016-10-08 01:52:55 0 0 event 2004-02-19T11:00:00-05:00 2004-02-19T00:00:00-05:00 2004-02-19T00:00:00-05:00 2004-02-19 16:00:00 2004-02-19 05:00:00 2004-02-19 05:00:00 2004-02-19T11:00:00-05:00 2004-02-19T00:00:00-05:00 America/New_York America/New_York datetime 2004-02-19 11:00:00 2004-02-19 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Faculty Candidate Seminar: Efficient Empirical Bayes Variable Selection and Estimation]]> 27279 Abstract: We propose an empirical Bayes method for variable selection and
coefficient estimation in linear regression models. The method is based on
a particular hierarchical Bayes formulation, and the estimator is shown to
be closely related to the LASSO estimator. Such a connection allows us to
take advantage of the recently developed quick LASSO algorithm to compute
the empirical Bayes estimate, and provides new ways to select the tuning
parameter in the LASSO method. Unlike previous empirical Bayes variable
selection methods, which in most practical situation can only be
implemented through a greedy stepwise algorithm, our method gives a global
solution efficiently. Simulations show that the proposed method compares
favorably with other variable selection and estimation methods in terms of
variable selection, estimation accuracy, and computation speed. This is
joint work with Professor Yi Lin.

]]> Barbara Christopher 1 1286538130 2010-10-08 11:42:10 1475891575 2016-10-08 01:52:55 0 0 event 2004-02-20T10:00:00-05:00 2004-02-20T00:00:00-05:00 2004-02-20T00:00:00-05:00 2004-02-20 15:00:00 2004-02-20 05:00:00 2004-02-20 05:00:00 2004-02-20T10:00:00-05:00 2004-02-20T00:00:00-05:00 America/New_York America/New_York datetime 2004-02-20 10:00:00 2004-02-20 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[ISyE Faculty Meeting]]> 27279 Anderson Chair Candidates. This meeting is for all who are interested in the subject matter.

If you are not able to make this meeting, but have comments to share, please contact Ellis Johnson.

]]> Barbara Christopher 1 1286538130 2010-10-08 11:42:10 1475891575 2016-10-08 01:52:55 0 0 event 2004-02-26T11:00:00-05:00 2004-02-26T00:00:00-05:00 2004-02-26T00:00:00-05:00 2004-02-26 16:00:00 2004-02-26 05:00:00 2004-02-26 05:00:00 2004-02-26T11:00:00-05:00 2004-02-26T00:00:00-05:00 America/New_York America/New_York datetime 2004-02-26 11:00:00 2004-02-26 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar::Semiparametric Maximum Likelihood Estimation with Estimation Equations: A New Approach for Censored Data in Survival Analyses]]> 27279 Semiparametric maximum likelihood estimation with estimating equations
(SMLE) is more flexible than the traditional methods such as the parametric maximum likelihood estimation, Cox's proportional hazards model, accelerated failure time model, quasi-likelihood, and generalized estimating equations with much less restrictions on distributions and regression-models. The needed information about distribution and regression structures is incorporated in estimating equations of the SMLE to improve the estimation quality of nonparametric methods. The likelihood of the SMLE in censored data cases involve several complicated implicit functions without closed-form expressions, and the first derivatives of the log-profile-likelihood cannot be expressed as summations of independent and identically distributed random variables.

For group-censored data and continuos data, it is verified that all the implicit functions are well defined, and the asymptotic distributions of the SMLE for model parameters and lifetime distributions are obtained.

A real life example with HIV data is presented to illustrate the application of SMLE method.

]]> Barbara Christopher 1 1286538131 2010-10-08 11:42:11 1475891575 2016-10-08 01:52:55 0 0 event 2004-02-26T12:00:00-05:00 2004-02-26T00:00:00-05:00 2004-02-26T00:00:00-05:00 2004-02-26 17:00:00 2004-02-26 05:00:00 2004-02-26 05:00:00 2004-02-26T12:00:00-05:00 2004-02-26T00:00:00-05:00 America/New_York America/New_York datetime 2004-02-26 12:00:00 2004-02-26 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics seminar:: DATA MODELING, QUANTILE/QUARTILE FUNCTIONS, CONFIDENCE INTERVALS, INTRODUCTORY STATISTICS REFORM]]> 27279 History of statistics is alive to me as I fondly recall my interaction with Eric Lehmann since receiving my Ph. D. in Berkeley in 1953. The 2003 Economics Nobel Prize (awarded for fundamental research in statistical time series analysis) reminds me of my joking complaint to diverse applied researchers: "why do you call it theory if I know it and applied research when you practice it?" I have continued to learn a lot about Quantiles and Nonparametric Data Modeling since my 1979 JASA paper. New methods have been developed (that some applied researchers consider a gold mine). Quantile data modeling is not practiced by most statisticians who are limited to sample median Q2, interquartile range IQR, and Q-Q probability plots. To estimate and test a parameter mu one starts with natural estimator mu^ ; we define statistic T(mu,mu^) increasing function of mu and with distribution (when mu is true parameter) equal to distribution of a random variable T (usually Normal(0,1), Student, or inverse average
chi-square). To test H_0:mu=mu_0 one computes or bounds P value(mu_0)=F_T(observed T(mu_0,mu^)); it is a distribution function of mu_0 (whose probability density one could derive). Define its inverse m^(u) by Q_T(u)=T(mu^(u),mu^); mu^(u), called the parameter with P-value u, is a quantile function which has a pseudo-Bayesian interpretation as the conditional quantile of mu given the data. The conventional confidence level 1-a confidence interval can
be shown to be mu^(a/2) define (and plot on same graph with exponential and normal) informative
quantile/quartile function Q/Q(u)=(Q(u)-midquartile)/2 IQR. Talk could also discuss confidence Q-Q plots, conditional quantile, comparison distribution, mid-distribution, and definition of sample quantiles, linear rank statistics, and sample variance.

]]> Barbara Christopher 1 1286538130 2010-10-08 11:42:10 1475891575 2016-10-08 01:52:55 0 0 event 2004-03-18T12:00:00-05:00 2004-03-18T00:00:00-05:00 2004-03-18T00:00:00-05:00 2004-03-18 17:00:00 2004-03-18 05:00:00 2004-03-18 05:00:00 2004-03-18T12:00:00-05:00 2004-03-18T00:00:00-05:00 America/New_York America/New_York datetime 2004-03-18 12:00:00 2004-03-18 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[INFORMS Atlanta Chapter Meeting]]> 27279 Richard Nelson, Director of Advanced Planning for the Consumer Products Group at Georgia Pacific, will speak on "Operations Research in the Supply Chain Arena". He will share techniques that have worked for his group, and offer insights into how to improve your chances for successful OR projects. Light refreshments will be served, and there will also be time to network with fellow OR professionals in the Atlanta community.

The meeting is open to all interested parties, and is free of charge. Please pass this information along to any associates whom you think might be interested.

The meeting will be in the Executive Classroom (Room 228) of the ISyE Main Entrance Bldg. (755 Ferst Drive, formerly the Dupree School of Management Building).

Here's a link to a map of the campus: http://www.isye.gatech.edu/visitors/maps/

There should be plenty of free parking in the area after 5:00 PM.

Kevin Geraghty (kevin@revenueresearch.com) is organizing an informal dinner after the meeting. Please contact him if you are interested in participating so he can make an appropriate reservation at a nearby restaurant.

We look forward to seeing you there. Please contact me if you have questions or suggestions, or if you wish to be added to the mailing list for future meetings.

]]> Barbara Christopher 1 1286538130 2010-10-08 11:42:10 1475891575 2016-10-08 01:52:55 0 0 event 2004-03-18T17:30:00-05:00 2004-03-18T00:00:00-05:00 2004-03-18T00:00:00-05:00 2004-03-18 22:30:00 2004-03-18 05:00:00 2004-03-18 05:00:00 2004-03-18T17:30:00-05:00 2004-03-18T00:00:00-05:00 America/New_York America/New_York datetime 2004-03-18 05:30:00 2004-03-18 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[The Sixth International ACM SIGCAPH Conference on Assistive Technologies]]> 27279 ASSETS 2004 (October 18-20, 2004) focuses on computer-based system design and its application to the special needs of persons with disabilities. The conference's scope spans special needs associated with speech, motor, hearing, and vision impairments; cognitive limitations; emotional and learning disabilities; and aging. Researchers and developers, from both academia and industry, are invited to meet to exchange ideas and present reports on new hardware and/or software advances related to these areas.

The conference program covers a multitude of topics relevant to assistive technologies and universal accessibility and is structured around technical papers, poster sessions, demonstrations, panels, the doctoral consortium, and a host of social events.

ASSETS 2004 will be held at the Georgia Tech Global Learning Center at Technology Square, a state-of-the-art meeting and accommodation facility that combines all the amenities and modern technologies of tomorrow with a prime midtown Atlanta location. The hotel and conference center is fully accessible to all participants.

]]> Barbara Christopher 1 1286538132 2010-10-08 11:42:12 1475891575 2016-10-08 01:52:55 0 0 event 2004-10-18T01:00:00-04:00 2004-10-18T01:00:00-04:00 2004-10-18T01:00:00-04:00 2004-10-18 05:00:00 2004-10-18 05:00:00 2004-10-18 05:00:00 2004-10-18T01:00:00-04:00 2004-10-18T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-18 01:00:00 2004-10-18 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Blind Identification and Visualization of Manufacturing Variation Sources]]> 27279 In modern manufacturing processes, large quantities of multivariate measurement data are routinely available through automated in-process sensing. The data generally contain a great deal of buried diagnostic information that can aid in identifying and eliminating major root causes of manufacturing variation. Traditional statistical process control (SPC) tools, which were designed for situations in which data are much less abundant, do not take full advantage of in-process measurement. In this talk I will discuss an approach that is much better suited for this scenario. The approach has origins in the sensor-array signal processing arena, where it is commonly referred to as blind source separation. The talk will cover basic blind source separation principals and the analogy between diagnosing multiple sources of manufacturing variation and separating multiple radar (for example) source signals from an antennae array. I will also discuss extending blind separation methods to be more effective and versatile in manufacturing. One advantage of the overall approach is that it lends itself well to graphical visualization methods for helping process operators and engineers understand the major root causes of manufacturing variation.

]]> Barbara Christopher 1 1286538130 2010-10-08 11:42:10 1475891575 2016-10-08 01:52:55 0 0 event 2004-05-11T12:00:00-04:00 2004-05-11T01:00:00-04:00 2004-05-11T01:00:00-04:00 2004-05-11 16:00:00 2004-05-11 05:00:00 2004-05-11 05:00:00 2004-05-11T12:00:00-04:00 2004-05-11T01:00:00-04:00 America/New_York America/New_York datetime 2004-05-11 12:00:00 2004-05-11 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[An Overview of Cost Allocation in Newsvendor Inventory Centralization]]> 27279 Consider a set of n stores with single item and single period demands with an option of centralized ordering

]]> Barbara Christopher 1 1286538130 2010-10-08 11:42:10 1475891575 2016-10-08 01:52:55 0 0 event 2004-05-25T12:00:00-04:00 2004-05-25T01:00:00-04:00 2004-05-25T01:00:00-04:00 2004-05-25 16:00:00 2004-05-25 05:00:00 2004-05-25 05:00:00 2004-05-25T12:00:00-04:00 2004-05-25T01:00:00-04:00 America/New_York America/New_York datetime 2004-05-25 12:00:00 2004-05-25 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[STATISTICS SEMINAR:: Confidence Intervals for High Quantiles of A Heavy Tailed Distribution]]> 27279 Estimating high quantiles plays an important role in the context of
risk management. This involves extrapolation of an unknown distribution
function beyond observations. Under consideration is construsting
confidence intervals for high quantiles of a heavy tailed distribution.
In this talk we introduce three methods, including the normal approximation
method based on Hill's estimator, the likelihood ratio method and the
data tilting method. Our simulation study shows that the data tilting
method has a better performance in terms of the accuracy of coverage
probabilities.

]]> Barbara Christopher 1 1286537947 2010-10-08 11:39:07 1475891571 2016-10-08 01:52:51 0 0 event 2004-08-26T13:00:00-04:00 2004-08-26T01:00:00-04:00 2004-08-26T01:00:00-04:00 2004-08-26 17:00:00 2004-08-26 05:00:00 2004-08-26 05:00:00 2004-08-26T13:00:00-04:00 2004-08-26T01:00:00-04:00 America/New_York America/New_York datetime 2004-08-26 01:00:00 2004-08-26 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Approximate Dynamic Programming for High-Dimensional Resource Allocation Problems]]> 27279 Dynamic programming has long been relegated to small problems due to the well-known "curse of dimensionality." We show that there are actually three curses of dimensionality, but that these can be overcome by using a different form of the optimality equations along with carefully chosen functional approximations. In particular, the use of separable, piecewise linear approximations of the value function is particularly well suited for discrete resource allocation problems, allowing us to solve dynamic programs where the dimensionality of the state variable is in the tens of thousands. We illustrate these methods in the context of several large-scale freight transportation applications, and discuss research issues that have arisen in these applications. One challenge has been the management of resources with complex attributes, which produces dynamic programs where the dimensionality of the state vector can measure in the millions. We show how hierarchical learning strategies can be used to produce effective approximations, helping to solve the "explore vs. exploit" dilemma that is well-known in approximate dynamic programming. As a byproduct, the value functions provide accurate gradient information, avoiding the need to perform statistically unreliable "what if" simulations to determine the effect of changes in fleet size and mix.

]]> Barbara Christopher 1 1286537943 2010-10-08 11:39:03 1475891571 2016-10-08 01:52:51 0 0 event 2004-11-04T11:00:00-05:00 2004-11-04T00:00:00-05:00 2004-11-04T00:00:00-05:00 2004-11-04 16:00:00 2004-11-04 05:00:00 2004-11-04 05:00:00 2004-11-04T11:00:00-05:00 2004-11-04T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-04 11:00:00 2004-11-04 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[STATISTICS SEMINAR: Gamma-Minimax Inference Without Tears]]> 27279 In the early 1950's Herbert Robbins (1915-2001)
introduced the
Gamma-Minimax or Bayes-Minimax Paradigm,
as a compromise between Minimax and Bayes
Paradigms. Gamma-Minimax actions rely on
Min-Max type theorems and are often hard or
impossible to find.

In this talk we overview linear approximations
to Gamma-minimax actions and demonstrate
that in many decision theoretic problems
linear approximations are not substantially affecting
the risk of the decision maker.

The talk is a mixture of educational and research overviews,
and does not assume prior exposure to minimaxity and
Gamma-minimaxity.

]]> Barbara Christopher 1 1286537946 2010-10-08 11:39:06 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-02T13:00:00-04:00 2004-09-02T01:00:00-04:00 2004-09-02T01:00:00-04:00 2004-09-02 17:00:00 2004-09-02 05:00:00 2004-09-02 05:00:00 2004-09-02T13:00:00-04:00 2004-09-02T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-02 01:00:00 2004-09-02 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[INFORMS Chapter Seminar :: OR Tools in Public Health]]> 27279 Dr. Michael L. Washington earned his B.S. in Industrial and Systems Engineering
from the University of Florida, and his M.S. and Ph.D. in Industrial Engineering
from the University of South Florida. He currently works in the National Immunization
Program at the Centers for Disease Control and Prevention in Atlanta, specializing
in applying OR techniques to public health issues. Dr. Washington has served
as a consultant for several foreign governments, and National Engineering Week
selected him as one of the top 16 young engineers in the nation in 2003. He was
nominated for a Service to America Medal for his Homeland Security efforts in
creating a mass smallpox vaccinations computer model to help local officials
prepare for a bio-terrorist attack.

A reception will precede the meeting at 5:30. The meeting is open to all interested
parties, and is free of charge. Refreshments will be served, and there will
also be time to network with fellow OR professionals in the Atlanta community.
The meeting will be in the Executive Classroom (Room 228) of the ISyE Main
Entrance Bldg. (755 Ferst Drive, formerly the Dupree School of Management Building
- same location as our previous meetings this year.) There is plenty of free
parking next to the building after 5:00 PM.

Map

http://www.isye.gatech.edu/visitors/maps/

Informs Chapter Website

http://www.isye.gatech.edu/~informs/atl_chapter/index.html

]]> Barbara Christopher 1 1286537942 2010-10-08 11:39:02 1475891571 2016-10-08 01:52:51 0 0 event 2004-11-04T17:30:00-05:00 2004-11-04T00:00:00-05:00 2004-11-04T00:00:00-05:00 2004-11-04 22:30:00 2004-11-04 05:00:00 2004-11-04 05:00:00 2004-11-04T17:30:00-05:00 2004-11-04T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-04 05:30:00 2004-11-04 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[IFAC Symposium]]> 27279 The IFAC Symposium will focus on Human-Machine Systems (HMS), Human Machine Interactions (HMI), and Human-Computer Interactions (HCI). Researchers and developers from both academia and industry are invited to meet to exchange ideas and present reports on new hardware and/or software advances. The symposium will be held September 7-9, 2004 in Atlanta, GA.

]]> Barbara Christopher 1 1286537948 2010-10-08 11:39:08 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-07T01:00:00-04:00 2004-09-07T01:00:00-04:00 2004-09-07T01:00:00-04:00 2004-09-07 05:00:00 2004-09-07 05:00:00 2004-09-07 05:00:00 2004-09-07T01:00:00-04:00 2004-09-07T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-07 01:00:00 2004-09-07 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Stochastics Seminar :: Asymptotically Optimal Control of a Queue with Impatient Customers]]> 27279 Barbara Christopher 1 1286537946 2010-10-08 11:39:06 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-08T05:00:00-04:00 2004-09-08T01:00:00-04:00 2004-09-08T01:00:00-04:00 2004-09-08 09:00:00 2004-09-08 05:00:00 2004-09-08 05:00:00 2004-09-08T05:00:00-04:00 2004-09-08T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-08 05:00:00 2004-09-08 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Stochastics Seminar :: Logical Control of Sequential Resource Allocation Systems]]> 27279 Spyros Reveliotis will continue his talk from last Wednesday.

Sequential resource allocation systems (RAS) constitute a pertinent modeling abstraction for the operational dynamics of a broad range of contemporary technological applications, including production systems, material handling and railway / monorail systems, e-commerce and other service-related processes, and even computational environments like those emerging in internet-based computing. In all these environments, a set of concurrently executing processes contest for the sequential exclusive acquisition of a finite set of re-usable resources that are necessary to support the execution of their various processing stages. The resulting resource allocation process must be controlled for (i) operational efficiency, a requirement giving rise to scheduling problems in the context of these environments, but also, for (ii) logical correctness and inherent consistency, a requirement addressed by an emerging logical control theory for these systems. The effective logical control of the aforementioned applications becomes an even more important problem as these environments migrate to extensively automated operational modes.

This talk will survey the state-of-the-art in RAS logical control. More specifically, the first part of the talk will provide a general description of the problem and a formal characterization of it in the Discrete Event Systems (Ramadge & Wonham

]]> Barbara Christopher 1 1286537945 2010-10-08 11:39:05 1475891571 2016-10-08 01:52:51 0 0 event 2004-11-10T04:00:00-05:00 2004-11-10T00:00:00-05:00 2004-11-10T00:00:00-05:00 2004-11-10 09:00:00 2004-11-10 05:00:00 2004-11-10 05:00:00 2004-11-10T04:00:00-05:00 2004-11-10T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-10 04:00:00 2004-11-10 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar :: Optimal Control of High Volume Assemble To Order Systems]]> 27279 We consider a high volume assemble-to-order system with mulitple products
and components. Our objective is to maximize infinite horizon expected
discounted profit. We show that optimal product prices and component
production capacity result in utilization near 100%, so the system is in
heavy traffic. We further show that heavy traffic remains the optimal
operating regime when customer orders must be assembled within a maximum
delay, and component production can be expedited at some additional cost.
In heavy traffic, the system exhibits a reduction in problem
dimensionaltiy. The limiting diffusion approximation has dimension equal
to the number of components (rather than the number of components plus the
number of products). We use this insight to propose discrete review
policies for sequencing product orders for assembly in both of the
aforementioned models. When delay constraints are present, we
additionally provide a policy for expediting components at discrete review
time points. We show our discrete review policies are asymptotically
optimal in heavy traffic.

]]> Barbara Christopher 1 1286537942 2010-10-08 11:39:02 1475891571 2016-10-08 01:52:51 0 0 event 2004-11-11T12:00:00-05:00 2004-11-11T00:00:00-05:00 2004-11-11T00:00:00-05:00 2004-11-11 17:00:00 2004-11-11 05:00:00 2004-11-11 05:00:00 2004-11-11T12:00:00-05:00 2004-11-11T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-11 12:00:00 2004-11-11 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[STATISTICS SEMINAR::Latent variable analysis for nonlinear structural modeling]]> 27279 Latent variable analysis is a multivariate statistical method that has been
useful in various applied fields. The method is now utilized in problems
arising from business intelligence, system engineering, and public health,
in addition to those in behavioral/social sciences. In this talk, a
general class of latent variable statistical models is considered in the
framework of structural equation system. In such a system, observed
variables are assumed to be related to latent factors, and relationships
among the unobservable factors are to be studied. Recent results in
handling various kinds of nonlinearity are presented. Model fitting,
estimation, and inference procedures are discussed.

]]> Barbara Christopher 1 1286537946 2010-10-08 11:39:06 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-09T13:00:00-04:00 2004-09-09T01:00:00-04:00 2004-09-09T01:00:00-04:00 2004-09-09 17:00:00 2004-09-09 05:00:00 2004-09-09 05:00:00 2004-09-09T13:00:00-04:00 2004-09-09T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-09 01:00:00 2004-09-09 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar:: Quasi-likelihood Estimation for GLM with Random Scales]]> 27279 This paper uses random scales similar to random effects used
in the generalized linear mixed models to describe
"inter-location" population variation in variance components
for modeling complicated data obtained from applications such as
antenna manufacturing. Our distribution studies lead to
a complicated integrated extended quasi-likelihood (IEQL) for
parameter estimations and large sample inference derivations.
Laplace's expansion and several approximation methods
are employed to simplify the IEQL estimation procedures.
Asymptotic properties of the approximate IEQL estimates are
derived for general structures of the covariance matrix of random scales.
Focusing on a few special covariance structures in simpler forms,
the authors further simplify IEQL estimates such that the typically used software
tools such as weighted regression can perform the estimates easily.
Moreover, these special cases
allow us to derive interesting asymptotic results in much more
compact expressions. Finally, numerical simulation results show that IEQL estimates
perform very well in several special cases studied.

]]> Barbara Christopher 1 1286537946 2010-10-08 11:39:06 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-15T14:00:00-04:00 2004-09-15T01:00:00-04:00 2004-09-15T01:00:00-04:00 2004-09-15 18:00:00 2004-09-15 05:00:00 2004-09-15 05:00:00 2004-09-15T14:00:00-04:00 2004-09-15T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-15 02:00:00 2004-09-15 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[ISyE Faculty Meeting]]> 27279 Barbara Christopher 1 1286537946 2010-10-08 11:39:06 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-16T11:15:00-04:00 2004-09-16T01:00:00-04:00 2004-09-16T01:00:00-04:00 2004-09-16 15:15:00 2004-09-16 05:00:00 2004-09-16 05:00:00 2004-09-16T11:15:00-04:00 2004-09-16T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-16 11:15:00 2004-09-16 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Dissertation Defense :: Dynamic Sequencing of Jobs on Conveyor Systems for Minimizing Changeovers]]> 27279 This research investigates the problem of constrained sequencing of a set of jobs on a conveyor system with the objective of minimizing setup cost. A setup cost is associated with extra material, labor, or energy required due to the change of attributes in consecutive jobs at processing stations. A finite set of attributes are considered in this research. Sequencing is constrained by the availability of two elements - storage buffers and conveyor junctions. The problem is motivated by the paint purge reduction problem at a major U.S. automotive manufacturer. First, a diverging junction with a sequence-independent setup cost and predefined attributes is modeled as an assignment problem and this model is extended by relaxing the initial assumptions in various ways. We also model the constrained sequencing problem with an off-line buffer and develop heuristics for efficiently getting a good quality solution by exploiting the special problem structure. Finally, we conduct sensitivity analysis using numerical experiments, explain the case study, and discuss the use of the simulation model as a supplementary tool for analyzing the constrained sequencing problem.

]]> Barbara Christopher 1 1286537944 2010-10-08 11:39:04 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-21T15:00:00-04:00 2004-09-21T01:00:00-04:00 2004-09-21T01:00:00-04:00 2004-09-21 19:00:00 2004-09-21 05:00:00 2004-09-21 05:00:00 2004-09-21T15:00:00-04:00 2004-09-21T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-21 03:00:00 2004-09-21 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Stochastics Seminar :: Inter-Departure Times in Base-Stock Inventory Queues]]> 27279 An inventory-queue is an inventory system controlled by a processing station with queueing. They are natural building blocks for supply chain models. An important and largely open issue for inventory queues is the characterization of their departure processes. In an inventory-queue, departures are triggered either by a job arrival when the output buffer is not empty or otherwise by a service completion. Such departures are more difficult to analyze than departures from a standard queue. The main results in this study are expressions for the probability distributions and squared coefficients of variation of inter-departure times for base-stock inventory-queues with birth-death production processes.

(Joint work with Liwei Bai (Georgia Tech), Liming Liu and Weixin Shang (Hong Kong Univ. of Sci. and Tech.)). Based on the paper, L. Bai, B. Fralix, L. Liu, and W. Shang. Inter-Departure Times in Base-Stock Inventory-Queues. Queueing Systems 47 (2004) 345-361.

]]> Barbara Christopher 1 1286537946 2010-10-08 11:39:06 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-22T05:00:00-04:00 2004-09-22T01:00:00-04:00 2004-09-22T01:00:00-04:00 2004-09-22 09:00:00 2004-09-22 05:00:00 2004-09-22 05:00:00 2004-09-22T05:00:00-04:00 2004-09-22T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-22 05:00:00 2004-09-22 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Stochastics Seminar :: Performance Modeling, Analysis, and Control of Capacitated Re-entrant Lines]]> 27279 The basic definition of the re-entrant line, which constitutes the typical abstraction for the formal modeling and analysis of the fab scheduling problem, considers only the job contest for the finite processing capacity of the system workstations, while ignoring completely the effects and complications arising from additional operational issues like the finite buffering capacity of the system workstation / production units. Moreover, the operational policies developed to control these logical aspects of the system behavior introduce additional constraints to the fab scheduling problem, that complicate it even further and, more importantly, invalidate prior characterizations of its optimal solutions.

Motivated by these remarks, we consider the problem of performance modeling, analysis and control of capacitated, flexibly automated re-entrant lines. Specifically, we develop an analytical framework for the modeling, analysis and control of capacitated re-entrant lines, which is based on Generalized Stochastic Petri nets (GSPN) framework. Furthermore, the underlying scheduling problem is transformed to a Markov Decision Process (MDP) problem and finally, we suggest a systematic, efficient and scalable approximating scheme, which is based on the Neuro-Dynamic Programming (NDP) theory, for the optimal scheduling policy characterized in the GSPN / MDP framework. The quality of the obtained approximations is experimentally assessed by

]]> Barbara Christopher 1 1286537945 2010-10-08 11:39:05 1475891571 2016-10-08 01:52:51 0 0 event 2004-11-17T04:00:00-05:00 2004-11-17T00:00:00-05:00 2004-11-17T00:00:00-05:00 2004-11-17 09:00:00 2004-11-17 05:00:00 2004-11-17 05:00:00 2004-11-17T04:00:00-05:00 2004-11-17T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-17 04:00:00 2004-11-17 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar:: Robust parameter design with feedback control]]> 27279 Robust parameter design has been widely used as a cost effective
tool to reduce process variability by appropriate selection of
control factors to make the process insensitive to noise.
However, when there exists strong noise factors in the process,
robust parameter design alone may not be effective and an on-line
control strategy can be used to compensate for the effect of
noise. In this paper, a parameter design methodology in the
presence of feedback control is developed. Systems with pure-gain
dynamic model are considered and the best proportional-integral
(PI) and minimum mean squared error (MMSE) control strategies are
developed by using robust parameter design. The proposed method is
illustrated using a real life example from a urea packing plant.

]]> Barbara Christopher 1 1286537944 2010-10-08 11:39:04 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-22T14:00:00-04:00 2004-09-22T01:00:00-04:00 2004-09-22T01:00:00-04:00 2004-09-22 18:00:00 2004-09-22 05:00:00 2004-09-22 05:00:00 2004-09-22T14:00:00-04:00 2004-09-22T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-22 02:00:00 2004-09-22 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Revenue Management]]> 27279 Barbara Christopher 1 1286537944 2010-10-08 11:39:04 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-22T15:15:00-04:00 2004-09-22T01:00:00-04:00 2004-09-22T01:00:00-04:00 2004-09-22 19:15:00 2004-09-22 05:00:00 2004-09-22 05:00:00 2004-09-22T15:15:00-04:00 2004-09-22T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-22 03:15:00 2004-09-22 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[ISyE Welcome Back Picnic]]> 27279 ISyE is hosting a Welcome Back Picnic for its students Thursday, September 23 from 11:30am - 1:30pm. It will be an old fashioned cookout with hotdogs, hamburgers, baked beans and more.

]]> Barbara Christopher 1 1286537944 2010-10-08 11:39:04 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-23T12:30:00-04:00 2004-09-23T01:00:00-04:00 2004-09-23T01:00:00-04:00 2004-09-23 16:30:00 2004-09-23 05:00:00 2004-09-23 05:00:00 2004-09-23T12:30:00-04:00 2004-09-23T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-23 12:30:00 2004-09-23 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[O&D-based Demand Driven Dispatch: Integrating Airline Scheduling, Pricing and Revenue Management for Short-term Re-fleeting]]> 27279 Barbara Christopher 1 1286537944 2010-10-08 11:39:04 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-29T13:00:00-04:00 2004-09-29T01:00:00-04:00 2004-09-29T01:00:00-04:00 2004-09-29 17:00:00 2004-09-29 05:00:00 2004-09-29 05:00:00 2004-09-29T13:00:00-04:00 2004-09-29T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-29 01:00:00 2004-09-29 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Ambiguous chance constrained problems and robust optimization]]> 27279 Let x denote a vector of n decision variables and Y denote a random vector. A constraint of the form P(f(x,Y) > 0) < eps
is called a chance constraint on the decision variable x. Optimization problems with chance constraints are notoriously hard to solve.

A simple strategy for solving chance constrained problems is to generate N samples according to the distribution P and then impose the constraints f(x,Y_i) < 0, for all i = 1, ..., N (*)
Since Y_i are random samples, there is no hope that decision
variables x that are feasible for (*) are all feasible for the chance
constraint with probability 1. Therefore, one has to allow a probability of error delta. Question: How large should N be as a function of eps and
delta ?

Recently, Calafiore and Campi showed that when f(x,Y) is a convex function of x for every fixed Y we only need N =O(n/delta log(1/eps)). Nemirovski and Shapiro have shown that if the function f(x,Y) is bi-affine and the distribution P has a "concentration-of-measure" property the number of samples required drops to N = O(n log(1/(eps*delta))).

In many applications of chance constrained problems the distribution P is not completely known, i.e. the distribution is ambiguous. The natural
constraint to impose in this setting is the ambiguous chance constraint:
max_{P in M} {P(f(x,Y) > 0)} < eps, where M is an uncertainty set of distributions. In this talk we discuss how to extend many results known for chance constrained problems to this more general setting. Robust deterministic optimization naturally arises
in these extensions by way of the Strassen-Dudley representation theorem.

(Joint work with Emre Erdogan)

Brief Bio: Garud Iyengar received his PhD in Electrical Engineering from Stanford University in 1998. Since then he has been with the Industrial Engineering and Operations Research (IEOR) department at Columbia
University where he is currently an Associate Professor.

]]> Barbara Christopher 1 1286537943 2010-10-08 11:39:03 1475891571 2016-10-08 01:52:51 0 0 event 2004-11-18T11:00:00-05:00 2004-11-18T00:00:00-05:00 2004-11-18T00:00:00-05:00 2004-11-18 16:00:00 2004-11-18 05:00:00 2004-11-18 05:00:00 2004-11-18T11:00:00-05:00 2004-11-18T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-18 11:00:00 2004-11-18 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Exploring Relaxation Induced Neighborhoods to Improve MIP Solutions]]> 27279 Given a feasible solution to a Mixed Integer Programming (MIP) model, a natural question is whether that solution can be improved using local search techniques. Local search has been applied very successfully in a variety of other combinatorial optimization domains. Unfortunately, local search relies extensively on the notion of
a solution neighborhood, and this neighborhood is almost always tailored to the structure of the particular problem being solved. A MIP model typically conveys little information about the underlying problem structure. This talk will consider two new approaches to exploring
interesting, domain-independent neighborhoods in MIP. The more
effective of the two, which we call Relaxation Induced Neighborhood Search (RINS), constructs a promising neighborhood using information
contained in the continuous relaxation of the MIP model. Neighborhood exploration is then formulated as a MIP model itself and solved recursively. The second, which we call guided dives, is a simple
modification of the MIP tree traversal order. Loosely speaking, it guides the search towards nodes that are close neighbors of the best known feasible solution. Extensive computational experiments on very
difficult MIP models show that both approaches outperform default CPLEX MIP and a previously described approach for exploring MIP neighborhoods (local branching) with respect to several different metrics. The metrics
we consider are quality of the best integer solution produced within a time limit, ability to improve a given integer solution (of both good and poor quality), and time required to diversify the search in order to find a new solution.

]]> Barbara Christopher 1 1286537944 2010-10-08 11:39:04 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-30T12:00:00-04:00 2004-09-30T01:00:00-04:00 2004-09-30T01:00:00-04:00 2004-09-30 16:00:00 2004-09-30 05:00:00 2004-09-30 05:00:00 2004-09-30T12:00:00-04:00 2004-09-30T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-30 12:00:00 2004-09-30 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar::American-style Options Pricing by Adaptive Simulation]]> 27279 We propose a novel simulation approach for pricing American-style contingent claims. We develop an adaptive policy search algorithm for searching the optimal policy in exercising an American-style option. The option price is obtained by first estimating the optimal option exercising policy and then evaluating the option with the estimated policy through simulation. Both high-biased and low-biased estimators of the option price are obtained. We show that the proposed algorithm leads to the convergence to the true optimal policy with probability one. This policy search algorithm requires little knowledge about the structure of the optimal policy and can be naturally implemented by parallel computing methods. As illustrative examples, computational results on pricing regular American options and American-Asian options are reported and they indicate that our algorithm is faster than certain alternative American option pricing algorithms reported in the literature. ((joint work with Sunjoo Lee).

]]> Barbara Christopher 1 1286537946 2010-10-08 11:39:06 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-30T13:00:00-04:00 2004-09-30T01:00:00-04:00 2004-09-30T01:00:00-04:00 2004-09-30 17:00:00 2004-09-30 05:00:00 2004-09-30 05:00:00 2004-09-30T13:00:00-04:00 2004-09-30T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-30 01:00:00 2004-09-30 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Faculty Meeting]]> 27279 As noted in ISyE related email.

]]> Barbara Christopher 1 1286537942 2010-10-08 11:39:02 1475891571 2016-10-08 01:52:51 0 0 event 2004-11-30T11:00:00-05:00 2004-11-30T00:00:00-05:00 2004-11-30T00:00:00-05:00 2004-11-30 16:00:00 2004-11-30 05:00:00 2004-11-30 05:00:00 2004-11-30T11:00:00-05:00 2004-11-30T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-30 11:00:00 2004-11-30 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Thesis Defense :: Dynamic Scheduling of Open Multiclass Queueing Networks in a Slowly Changing Environment]]> 27279 We study the scheduling policies for high-speed communication networks with time varying traffic patterns. We model such networks as open multiclass queueing networks operating in a slowly changing environment.

We assume that there are finite environment states and the changing environment is modeled as a general stochastic process which takes discrete values. At each state of the environment, the network operates as a queueing network where each server may serve multiple classes of customers. In this study, we establish a framework to search for asymptotically optimal scheduling policies for such queueing networks. We first show that open queueing networks in a slowly changing environment can be approximated by their fluid analog, stochastic fluid models, when the network speed increases. Given a solution of the stochastic fluid model, we provide a method to derive suitable scheduling policies for the original queueing networks. We further show that the queueing networks operating under the derived policies converge to the corresponding stochastic fluid model . This result implies that the derived scheduling policies are asymptotically optimal if the given stochastic fluid model solution is optimal. We also study a stochastic fluid model to investigate the optimal resource allocation policies of Web servers serving heterogeneous classes where the Web servers may be overloaded and operate under Quality of Service contracts.

]]> Barbara Christopher 1 1286537944 2010-10-08 11:39:04 1475891571 2016-10-08 01:52:51 0 0 event 2004-09-30T16:00:00-04:00 2004-09-30T01:00:00-04:00 2004-09-30T01:00:00-04:00 2004-09-30 20:00:00 2004-09-30 05:00:00 2004-09-30 05:00:00 2004-09-30T16:00:00-04:00 2004-09-30T01:00:00-04:00 America/New_York America/New_York datetime 2004-09-30 04:00:00 2004-09-30 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Advanced Design Integration for Radical Energy Efficiency]]> 27279 Barbara Christopher 1 1286538130 2010-10-08 11:42:10 1475891571 2016-10-08 01:52:51 0 0 event 2004-03-17T16:00:00-05:00 2004-03-17T00:00:00-05:00 2004-03-17T00:00:00-05:00 2004-03-17 21:00:00 2004-03-17 05:00:00 2004-03-17 05:00:00 2004-03-17T16:00:00-05:00 2004-03-17T00:00:00-05:00 America/New_York America/New_York datetime 2004-03-17 04:00:00 2004-03-17 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Stochastics Seminar :: Derivative Free Algorithms for Stochastic Optimization]]> 27279 In this talk, we consider a class of trust region algorithms to solve
stochastic programming problems that satisfy the following properties:

(1) The objective function can only be evaluated with some error,
for example by and at high computational cost.

b) The error can be decreased with more computational effort.
c) The higher order derivatives of the objective function are unavailable.
Though our work is motivated from problems arising in stochastic simulation
optimization (Eg.Revenue Management), such optimization problems also commonly arise in
engineering design (Eg. helicopter rotor blade design).
Due to the high cost of evaluating the objective function, our aim is
to develop convergent algorithms that can solve such problems
while requiring the fewest possible number of evaluations of the
objective function.

When the objective function and its gradient can be evaluated easily
and exactly, a typical trust region algorithm works as follows.
At each iteration, we first construct a polynomial model function, typically a
truncated Taylor series expansion of the objective at the
current iterate, that approximates the objective function
in a certain neighborhood of the current iterate called
the trust region. We then optimize this model function within the trust
region. Depending on whether the resulting
optimal solution has a lower objective function value or not, we
either set this as the next iterate or conversely, alter the trust
region size and/or the model function appropriately and try again.

Since in our case, the objective function and its higher order
derivatives cannot be evaluated exactly, we cannot use a Taylor series
based model function. Accordingly, we propose
alternative linear or quadratic polynomial
model functions that are constructed by linear regression using only
sample average approximations of the objective, evaluated at points
in the neighborhood of the current iterate. We describe the various
changes that have to be made to the traditional trust region framework
in order to successfully construct and control the accuracy of such regression
based model functions and present the convergence theory for the
resulting modified trust region algorithm. Finally, we provide
computational results for such an algorithm run on selected problems
from the CUTE test set.

]]> Barbara Christopher 1 1286537945 2010-10-08 11:39:05 1475891571 2016-10-08 01:52:51 0 0 event 2004-12-01T04:00:00-05:00 2004-12-01T00:00:00-05:00 2004-12-01T00:00:00-05:00 2004-12-01 09:00:00 2004-12-01 05:00:00 2004-12-01 05:00:00 2004-12-01T04:00:00-05:00 2004-12-01T00:00:00-05:00 America/New_York America/New_York datetime 2004-12-01 04:00:00 2004-12-01 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Second Annual ISyE Ph.D. Pre-game Picnic]]> 27279 I am pleased to announce that the Second Annual ISyE Ph.D. Pregame Picnic will be held this Friday, October 1 from 4-7 P.M. on the IC Lawn, weather permitting.

This event is FREE FOR ISyE Ph.D. STUDENTS, FACULTY, AND STAFF. We encourage people to bring their families and close friends, as one of our goals is to have a "family-oriented" event. However, to cover expenses, there is a nominal $3 fee for all adult guests. There is no cost for children.

The menu will include, but not be limited to: hamburgers, veggie burgers, beef hot dogs, grilled chicken, vegetarian baked beans, and potato salad.
Water and soda will be provided as well. ALCOHOL IS PROHIBITED.

We are also planning to have a volleyball setup and, if enough interested faculty attend, a faculty vs student volleyball match.

If you would like to attend this event, please respond to this email no later than Thursday, September 30, at 5 P.M. with the following
information:

Name:
Year in Program (2nd, 3rd, 4th, etc.):
Area of Concentration or Specialty (EDA, Optimization, Statistics, etc):
Number of Adult Guests:
Number of Children Guests:
Names of Adult Guests:
Names of Children Guests:

We also could use some volunteers to help with the following:

1. Setup of tables and chairs at approximately 3:00 P.M.
2. Volleyball setup at approximately 3:30 P.M.
3. Clean-up from approximately 7:30-9:00 P.M.

If you are available and are willing to volunteer for one or more of these, please indicate that in your reply as well. Your help would be greatly appreciated.

Thank you, and we look forward to enjoying your fellowship on Friday!!! :)

]]> Barbara Christopher 1 1286537943 2010-10-08 11:39:03 1475891571 2016-10-08 01:52:51 0 0 event 2004-10-01T17:00:00-04:00 2004-10-01T01:00:00-04:00 2004-10-01T01:00:00-04:00 2004-10-01 21:00:00 2004-10-01 05:00:00 2004-10-01 05:00:00 2004-10-01T17:00:00-04:00 2004-10-01T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-01 05:00:00 2004-10-01 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[ISyE Meet & Mingle]]> 27279 ISyE will be hosting a reception in the main building lounge area for families of IE students to MEET AND MINGLE with the faculty! This is an opportunity for parents to meet their child's teachers. We do not plan a formal program. Please mark this on your calendars and attend!

]]> Barbara Christopher 1 1286537944 2010-10-08 11:39:04 1475891571 2016-10-08 01:52:51 0 0 event 2004-10-01T17:00:00-04:00 2004-10-01T01:00:00-04:00 2004-10-01T01:00:00-04:00 2004-10-01 21:00:00 2004-10-01 05:00:00 2004-10-01 05:00:00 2004-10-01T17:00:00-04:00 2004-10-01T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-01 05:00:00 2004-10-01 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Stochastics Seminar :: Generalized Jackson Networks with Reneging and the Regulated Ornstein-Uhlenbeck Process]]> 27279 We consider a generalized Jackson network with reneging customers in heavy traffic. In particular, each customer joining a particular station may abandon the network if his service does not begin within a station-dependent, exponential, amount of time. We establish that in heavy traffic this system can be approximated by a multi-dimensional regulated Ornstein-Uhlenbeck process (RO-U). We also derive necessary and sufficient conditions under which the RO-U has a stationary distribution, explicitly determining the analytical form of this distribution under some special conditions.
(Joint with Amy Ward)

]]> Barbara Christopher 1 1286537945 2010-10-08 11:39:05 1475891571 2016-10-08 01:52:51 0 0 event 2004-10-06T05:00:00-04:00 2004-10-06T01:00:00-04:00 2004-10-06T01:00:00-04:00 2004-10-06 09:00:00 2004-10-06 05:00:00 2004-10-06 05:00:00 2004-10-06T05:00:00-04:00 2004-10-06T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-06 05:00:00 2004-10-06 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar:: BAYESIAN DECISION THEORETIC SCALE-ADAPTIVE ESTIMATION OF A LOG-SPECTRAL DENSITY]]> 27279 The problem of estimating the log-spectrum of a
stationary Gaussian time series by Bayesianly induced
shrinkage of empirical wavelet coefficients is studied.
A model in the wavelet domain that
accounts for distributional properties of the log-periodogram
at levels of fine detail and approximate normality at
coarse levels in the wavelet decomposition, is proposed.
The smoothing procedure, called BAMS-LP (Bayesian Adaptive Multiscale
Shrinker of Log-Periodogram),
ensures that the reconstructed log-spectrum is
as noise-free as possible. It is also shown that the resulting
Bayes estimators are asymptotically optimal (in the frequentist sense).

Comparisons with non-wavelet and wavelet-non-Bayesian
methods are discussed.

This is a joint work with Marianna Pensky from UCF.

]]> Barbara Christopher 1 1286538129 2010-10-08 11:42:09 1475891571 2016-10-08 01:52:51 0 0 event 2004-03-25T12:00:00-05:00 2004-03-25T00:00:00-05:00 2004-03-25T00:00:00-05:00 2004-03-25 17:00:00 2004-03-25 05:00:00 2004-03-25 05:00:00 2004-03-25T12:00:00-05:00 2004-03-25T00:00:00-05:00 America/New_York America/New_York datetime 2004-03-25 12:00:00 2004-03-25 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar :: CUSUM charts for preliminary analysis of individual observations]]> 27279 A preliminary Cusum chart based on individual observations is developed from
the uniformly most powerful test for the detection of linear trends. This
Cusum chart is compared with several of its alternatives which are based on
the likelihood ratio test and on transformations of standardized recursive
residuals on which for instance the Q-chart methodology is based. It turns
out that the proposed Cusum chart is not only superior in the detection of
linear trend out-of-control conditions, but also in the detection of other
out-of-control situations considered in this paper. Approximate control
limits, determined from simulation, and an example of its use in practice
are given for the proposed Cusum chart. (Joint work with Ronald Does,
University of Amsterdam).

]]> Barbara Christopher 1 1286537943 2010-10-08 11:39:03 1475891571 2016-10-08 01:52:51 0 0 event 2004-10-06T14:00:00-04:00 2004-10-06T01:00:00-04:00 2004-10-06T01:00:00-04:00 2004-10-06 18:00:00 2004-10-06 05:00:00 2004-10-06 05:00:00 2004-10-06T14:00:00-04:00 2004-10-06T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-06 02:00:00 2004-10-06 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics seminar:: Modeling and Analysis of Population Evolution Data]]> 27279 The last two decades have seen an explosion of novel ideas in the areas of biotechnology and information technology. The impact of these discoveries are being felt in diverse areas such as genetics, finance, e-commerce, biology, and internet traffic, to mention a few. The scientific experiments carried out using these modern technologies are yielding data that possess an "evolutionary branching process like structure". In this talk I will describe statistical models and methodologies to understand, analyze, and interpret the data emerging from these experiments. More specifically, I will focus on the data resulting from polymerase chain reaction experiments.

The modeling and the methodological part of this talk are motivated by the following three scientific questions:

(a) How does one "statistically quantify" the unknown amount of gene in a "sample" using PCR amplification methods?
(b) What are the factors affecting the amplification rate of a PCR experiment?
(c) How does one efficiently design experiments to study the mutations induced by PCR experiments?

Statistical quantification can lead to an accurate estimate of the HIV-1 viral load in HIV-1 infected patients. This not only helps with disease diagnosis but also in the disease prognosis. Answers to questions (b) and (c) will facilitate a better understanding of the dynamics of a PCR process.

]]> Barbara Christopher 1 1286538129 2010-10-08 11:42:09 1475891571 2016-10-08 01:52:51 0 0 event 2004-04-01T12:00:00-05:00 2004-04-01T00:00:00-05:00 2004-04-01T00:00:00-05:00 2004-04-01 17:00:00 2004-04-01 05:00:00 2004-04-01 05:00:00 2004-04-01T12:00:00-05:00 2004-04-01T00:00:00-05:00 America/New_York America/New_York datetime 2004-04-01 12:00:00 2004-04-01 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Stochastics Seminar :: Tandem Lines with Dedicated and Flexible Servers]]> 27279 Consider a tandem queueing network with $Ngeq 2$ stations, $Mgeq 1$ servers, infinite supply of jobs in front of station 1, infinite room for completed jobs after station $N$, and either a finite or infinite buffer between any two consecutive stations. We study the dynamic allocation of servers to stations with the goal of maximizing the long-run average throughput, assuming that only a subset of the servers are flexible in that they are able to work at several stations, with the remaining servers being dedicated to particular stations.

Authors: Sigrun Andradottir, Hayriye Ayhan, and Douglas G. Down

]]> Barbara Christopher 1 1286537945 2010-10-08 11:39:05 1475891571 2016-10-08 01:52:51 0 0 event 2004-10-13T05:00:00-04:00 2004-10-13T01:00:00-04:00 2004-10-13T01:00:00-04:00 2004-10-13 09:00:00 2004-10-13 05:00:00 2004-10-13 05:00:00 2004-10-13T05:00:00-04:00 2004-10-13T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-13 05:00:00 2004-10-13 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics seminar:: Some recent developments in Stochastic Programming]]> 27279 In this talk I will discuss two recent developments in the theory and
practice of stochastic programming. Namely, development of Monte Carlo
simulation based optimization techniques and mathematical theory of risk
measures.

]]> Barbara Christopher 1 1286538129 2010-10-08 11:42:09 1475891571 2016-10-08 01:52:51 0 0 event 2004-04-08T13:00:00-04:00 2004-04-08T01:00:00-04:00 2004-04-08T01:00:00-04:00 2004-04-08 17:00:00 2004-04-08 05:00:00 2004-04-08 05:00:00 2004-04-08T13:00:00-04:00 2004-04-08T01:00:00-04:00 America/New_York America/New_York datetime 2004-04-08 01:00:00 2004-04-08 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar:: Multi-Level Spatial Modelling with Application in Logistics System Analysis]]> 27279 Multi-level spatial models are proposed to approximate large size
logistics network systems. The linkage across different levels of spatial models
is specified through estimating equations to utilize information considered at different
stages. The multi-level models are applied in decision analysis of logistics systems
such as facility location allocation and demand forecasting problems. System
reliability of logistics service is introduced to characterize the uncertainty of
supply chain disruptions. In particular, a sum-of-disjoint-product (SDP) method
is presented to evaluate the system reliability. Real-life examples show the potential
use of the models in characterizing logistics networks, assisting logistics planning
processes and evaluating network designs for dealing with unexpected supply chain
disruption. (Joint work with J.-C. Lu and P. H. Kvam).

]]> Barbara Christopher 1 1286537943 2010-10-08 11:39:03 1475891571 2016-10-08 01:52:51 0 0 event 2004-10-13T14:00:00-04:00 2004-10-13T01:00:00-04:00 2004-10-13T01:00:00-04:00 2004-10-13 18:00:00 2004-10-13 05:00:00 2004-10-13 05:00:00 2004-10-13T14:00:00-04:00 2004-10-13T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-13 02:00:00 2004-10-13 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics seminar:: Finding the Best Regular Resolution IV Fractional Factorial Designs]]> 27279 Two-level fractional factorial designs are among the most useful statistical designs for engineering applications. This talk will review recent literature regarding the construction of these designs. Topics will include alternative criteria based on the alias length pattern, and uses of the row coincidence matrix to help distinguish between designs. A recently attempted complete enumeration of resolution IV designs for 128-run designs will be described. The talk will conclude with the open problem of how to search for optimal resolution IV designs for even larger run size.

]]> Barbara Christopher 1 1286538129 2010-10-08 11:42:09 1475891571 2016-10-08 01:52:51 0 0 event 2004-04-15T13:00:00-04:00 2004-04-15T01:00:00-04:00 2004-04-15T01:00:00-04:00 2004-04-15 17:00:00 2004-04-15 05:00:00 2004-04-15 05:00:00 2004-04-15T13:00:00-04:00 2004-04-15T01:00:00-04:00 America/New_York America/New_York datetime 2004-04-15 01:00:00 2004-04-15 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Beyond the Scope of Interior Point Polynomial Time...]]> 27279 In all known polynomial time algorithms of nonlinear convex optimization, the computational effort per iteration grows nonlinearly with the design dimension n of the problem (typically, as n3). As a result, in the case of extremely large-scale (tens and hundreds thousands of variables) convex programs, a single iteration of a polynomial time algorithm can become too expensive to be practical. In these cases one is enforced to use

]]> Barbara Christopher 1 1286537943 2010-10-08 11:39:03 1475891571 2016-10-08 01:52:51 0 0 event 2004-10-14T12:00:00-04:00 2004-10-14T01:00:00-04:00 2004-10-14T01:00:00-04:00 2004-10-14 16:00:00 2004-10-14 05:00:00 2004-10-14 05:00:00 2004-10-14T12:00:00-04:00 2004-10-14T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-14 12:00:00 2004-10-14 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Second Annual ISyE Spring Festival]]> 27279 The school year is coming to an end, and ISyE is hosting its second annual Spring Festival for our students this Friday, April 16 from 11:00am - 1:00pm.

Once again, our festival will feature a Mexican Fajita & Taco Bar.

]]> Barbara Christopher 1 1286537948 2010-10-08 11:39:08 1475891571 2016-10-08 01:52:51 0 0 event 2004-04-16T12:00:00-04:00 2004-04-16T01:00:00-04:00 2004-04-16T01:00:00-04:00 2004-04-16 16:00:00 2004-04-16 05:00:00 2004-04-16 05:00:00 2004-04-16T12:00:00-04:00 2004-04-16T01:00:00-04:00 America/New_York America/New_York datetime 2004-04-16 12:00:00 2004-04-16 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[ISyE Ph.D. End of the Year Bash]]> 27279 I am pleased to announce that the ISyE Ph.D. END OF THE YEAR BASH, sponsored by the Georgia Tech Chapter of INFORMS, will be held on FRIDAY, APRIL 16, 2004 from 3-7 P.M. on the LAWN BEHIND THE INSTRUCTIONAL CENTER.

For those of you who came to our ISyE tailgate party this past October, this event will be very similar. We will have a picnic-style setup again will GRILLED MEATS, CHIPS, AND DRINKS. However, this time, we will have FRISBEES AND A VOLLEYBALL SET-UP in addition to other games and activities for your enjoyment.

With regard to food, there will be NON-MEAT OPTIONS available for vegetarians. In addition, there will be NO PORK among the meat products.

PLEASE RSVP NO LATER THAN THURSDAY, APRIL 15 USING THE FORM BELOW if you plan to attend. Like last time, THERE IS A $2 CHARGE FOR ALL ADULT GUESTS, BUT NO CHARGE FOR CHILDREN. So, for those of you with families and/or significant others, we encourage you to bring them, if possible.

Name:
Years in ISyE:
Number of Guests:
Names of Guests (Kids in Parentheses):
If Date is Moved to 4/30 Due To Rain, Can You Attend?

(The rest of the form is for Ph.D. students only.)

Concentration:
Advisor:

In case of rain, the alternate date for the event has been set for Friday, April 30.

This event is being sponsored by the Georgia Tech Chapter of INFORMS, with approval from its faculty advisor Dr. Dave Goldsman.

Thank you.

W. Brad Jones

_________________________________
_________________________________
W. Brad Jones, Ph.D. Student
Georgia Institute of Technology
School of Industrial and Systems Engineering
310 ISyE Main Building
Atlanta, GA 30332

]]> Barbara Christopher 1 1286537948 2010-10-08 11:39:08 1475891571 2016-10-08 01:52:51 0 0 event 2004-04-16T16:00:00-04:00 2004-04-16T01:00:00-04:00 2004-04-16T01:00:00-04:00 2004-04-16 20:00:00 2004-04-16 05:00:00 2004-04-16 05:00:00 2004-04-16T16:00:00-04:00 2004-04-16T01:00:00-04:00 America/New_York America/New_York datetime 2004-04-16 04:00:00 2004-04-16 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Stochastics Seminar :: Dynamic Scheduling in Stochastic Processing Networks]]> 27279 We consider a class of stochastic processing networks which are capable of modeling semiconductor wafer fabrication facilities, networks of data switches, and large scale call centers.

Assume the networks satisfy a so-called resource pooling condition. We prove a maximum pressure policy asymptotically minimizes the workload processes in heavy traffic. A key to the proof is to show the network processes exhibit state space collapse.
(joint with Jim Dai)

]]> Barbara Christopher 1 1286537945 2010-10-08 11:39:05 1475891571 2016-10-08 01:52:51 0 0 event 2004-10-20T05:00:00-04:00 2004-10-20T01:00:00-04:00 2004-10-20T01:00:00-04:00 2004-10-20 09:00:00 2004-10-20 05:00:00 2004-10-20 05:00:00 2004-10-20T05:00:00-04:00 2004-10-20T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-20 05:00:00 2004-10-20 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics seminar:: SELC : Sequential Elimination of Level Combinations by Means of Modified Genetic Algorithms]]> 27279 To search for an optimal design in a large search space, Wu, Mao, Ma
(1990) suggested the SEL-method to find an optimal setting. Genetic
algorithms (GA) can be used to improve upon this method. To make the
search procedure more efficient, new ideas of forbidden array and weighted
mutation are introduced. Relaxing the condition of orthogonality, GA is
able to accommodate a variety of design points which allows more
flexibility and enhances the chance of getting the best setting in fewer
runs, particularly in the presence of interactions. The search procedure
is enriched by a Bayesian method for identifying the important main
effects and two-factor interactions. Illustration is given with the
optimization of three functions, one of which is from Shekel's family.

]]> Barbara Christopher 1 1286537948 2010-10-08 11:39:08 1475891571 2016-10-08 01:52:51 0 0 event 2004-04-22T13:00:00-04:00 2004-04-22T01:00:00-04:00 2004-04-22T01:00:00-04:00 2004-04-22 17:00:00 2004-04-22 05:00:00 2004-04-22 05:00:00 2004-04-22T13:00:00-04:00 2004-04-22T01:00:00-04:00 America/New_York America/New_York datetime 2004-04-22 01:00:00 2004-04-22 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar:: Geometric Isomorphism and Minimum Aberration for Factorial Designs with Quantitative Factors]]> 27279 Factorial designs have broad applications in agriculture, engineering and scientific studies. In constructing and studying properties of factorial designs, traditional design theory treats all factors as nominal. However, this is not appropriate for experiments that involve quantitative factors. For designs with quantitative factors, level permutation of one or more factors in a design matrix could result in different geometric structures, and, thus, different design properties. In this paper indicator functions are introduced to represent factorial designs. A polynomial form of indicator functions is used to characterize the geometric structure of those designs. Geometric isomorphism is defined for classifying designs with quantitative factors. Based on indicator functions, a new aberration criteria is proposed and some minimum aberration designs are presented. (This talk is based on a joint work with Kenny Q. Ye, Albert Einstein College of Medicine)

]]> Barbara Christopher 1 1286537943 2010-10-08 11:39:03 1475891571 2016-10-08 01:52:51 0 0 event 2004-10-20T14:00:00-04:00 2004-10-20T01:00:00-04:00 2004-10-20T01:00:00-04:00 2004-10-20 18:00:00 2004-10-20 05:00:00 2004-10-20 05:00:00 2004-10-20T14:00:00-04:00 2004-10-20T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-20 02:00:00 2004-10-20 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Natural Systems Seminar]]> 27279 Barbara Christopher 1 1286537948 2010-10-08 11:39:08 1475891571 2016-10-08 01:52:51 0 0 event 2004-04-30T12:00:00-04:00 2004-04-30T01:00:00-04:00 2004-04-30T01:00:00-04:00 2004-04-30 16:00:00 2004-04-30 05:00:00 2004-04-30 05:00:00 2004-04-30T12:00:00-04:00 2004-04-30T01:00:00-04:00 America/New_York America/New_York datetime 2004-04-30 12:00:00 2004-04-30 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Emergency Room Overcrowding: An OR Analysis]]> 27279 Since 9/11, emergency rooms have come under closer scrutiny as the question of hospitals

]]> Barbara Christopher 1 1286537943 2010-10-08 11:39:03 1475891571 2016-10-08 01:52:51 0 0 event 2004-10-21T12:00:00-04:00 2004-10-21T01:00:00-04:00 2004-10-21T01:00:00-04:00 2004-10-21 16:00:00 2004-10-21 05:00:00 2004-10-21 05:00:00 2004-10-21T12:00:00-04:00 2004-10-21T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-21 12:00:00 2004-10-21 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar :: Enterprise Risk Management: A New Discipline That Calls For Research Innovations]]> 27279 Drawing from his academic/industry experience in risk management, Dr. Wang will introduce this new emerging discipline of ERM. He will start with a rather local view of statistical pricing theory and risk aggregation analytics, and then zoom out to the big picture of enterprise risks. He will discuss why ERM requires multidisciplinary collaborations and fresh looks of the theoretical foundation of risk. It will be an interesting mix of cutting-edge risk theories and common risk issues that everyone can relate to. The speaker wants to inspire young research minds to enter this new fertile field and produce highly relevant research.

]]> Barbara Christopher 1 1286537946 2010-10-08 11:39:06 1475891571 2016-10-08 01:52:51 0 0 event 2004-10-28T13:00:00-04:00 2004-10-28T01:00:00-04:00 2004-10-28T01:00:00-04:00 2004-10-28 17:00:00 2004-10-28 05:00:00 2004-10-28 05:00:00 2004-10-28T13:00:00-04:00 2004-10-28T01:00:00-04:00 America/New_York America/New_York datetime 2004-10-28 01:00:00 2004-10-28 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Stochastics Seminar :: Logical Control of Sequential Resource Allocation Systems]]> 27279 Sequential resource allocation systems (RAS) constitute a pertinent modeling abstraction for the operational dynamics of a broad range of contemporary technological applications, including production systems, material handling and railway / monorail systems, e-commerce and other service-related processes, and even computational environments like those emerging in internet-based computing. In all these environments, a set of concurrently executing processes contest for the sequential exclusive acquisition of a finite set of re-usable resources that are necessary to support the execution of their various processing stages. The resulting resource allocation process must be controlled for (i) operational efficiency, a requirement giving rise to scheduling problems in the context of these environments, but also, for (ii) logical correctness and inherent consistency, a requirement addressed by an emerging logical control theory for these systems. The effective logical control of the aforementioned applications becomes an even more important problem as these environments migrate to extensively automated operational modes.

This talk will survey the state-of-the-art in RAS logical control. More specifically, the first part of the talk will provide a general description of the problem and a formal characterization of it in the Discrete Event Systems (Ramadge & Wonham

]]> Barbara Christopher 1 1286537945 2010-10-08 11:39:05 1475891571 2016-10-08 01:52:51 0 0 event 2004-11-03T04:00:00-05:00 2004-11-03T00:00:00-05:00 2004-11-03T00:00:00-05:00 2004-11-03 09:00:00 2004-11-03 05:00:00 2004-11-03 05:00:00 2004-11-03T04:00:00-05:00 2004-11-03T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-03 04:00:00 2004-11-03 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Distributed Simulation for Decision Support in Semiconductor Supply Chains]]> 27279 Peter Lendermann is a Senior Scientist in the Production and Logistics Planning Group at Singapore Institute of Manufacturing Technology (SIMTech). Previously he was a Managing Consultant with agiplan in Germany where his focus was on the areas of supply chain management and production planning. He also worked as a Research Associate at the European Laboratory for Particle Physics CERN in Geneva (Switzerland) and Nagoya University (Japan). He obtained a Diploma in Physics from the University of Munich (Germany), a Doctorate in Applied Physics from Humboldt-University in Berlin (Germany) and a Master in International Economics and Management from Bocconi-University in Milan (Italy). His research interests include discrete event simulation as well as modeling and analysis of manufacturing and logistics systems.

Modeling and simulation is widely regarded as one of the breakthrough technologies that will accelerate progress in addressing the grand challenges facing manufacturing in the next decade. In this seminar, new research challenges arising from the increased criticality of inter-factory dependencies in today

]]> Barbara Christopher 1 1286537948 2010-10-08 11:39:08 1475891571 2016-10-08 01:52:51 0 0 event 2004-06-08T12:00:00-04:00 2004-06-08T01:00:00-04:00 2004-06-08T01:00:00-04:00 2004-06-08 16:00:00 2004-06-08 05:00:00 2004-06-08 05:00:00 2004-06-08T12:00:00-04:00 2004-06-08T01:00:00-04:00 America/New_York America/New_York datetime 2004-06-08 12:00:00 2004-06-08 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar :: De-noising signals of unknown local structure]]> 27279 We focus on recovering a non-parametric signal observed in Gaussian noise along an equidistant $d$-dimensional grid. Typical nonparametric regression estimates are aimed at recovering smooth signals $f$ and utilize the fact that such an $f$ is locally well approximated by an algebraic polynomial; thus, we can recover $f$ at a point from nearby observations as if $f$ were a polynomial, which is an easy-to-estimate entity. The research to be outlined in the talk is motivated by the simple observation that polynomials are not the only ``easy to estimate'' entities; the latter property is shared, e.g., by products of polynomials and harmonic oscillations. However, the traditional nonparametric techniques fail to recover signals of the latter type, except for the case when the frequencies of oscillations are known in advance or are low; the reason is that a good estimate of a product of algebraic polynomial and a harmonic oscillation requires a priori knowledge of the frequencies. In the talk, we present a kind of universal nonparametric estimate, based on Linear Programming, with the following property: whenever the signal to be estimated admits an ``easy to estimate'' local approximation $g$ (one which can be recovered well by an {sl unknown in advance} convolution filter), as it is the case for smooth signals, products of smooth signals and harmonic oscillations, etc., our estimate recovers the signal nearly as well as a hypothetical estimate utilizing this ``existing in the nature'' (and unknown in reality) filter. We demonstrate also that the family of ``easy to estimate'' signals is pretty rich, specifically, contains a number of important generic families of signals and is closed with respect to basic operations like modulation $g(x)mapsto g(x)cos(omega^Tx+phi)$ and summation.

]]> Barbara Christopher 1 1286537942 2010-10-08 11:39:02 1475891571 2016-10-08 01:52:51 0 0 event 2004-11-03T13:00:00-05:00 2004-11-03T00:00:00-05:00 2004-11-03T00:00:00-05:00 2004-11-03 18:00:00 2004-11-03 05:00:00 2004-11-03 05:00:00 2004-11-03T13:00:00-05:00 2004-11-03T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-03 01:00:00 2004-11-03 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[ISyE Graduate Student Pizza Party]]> 27279 Please join us in welcoming the new graduate students to ISyE.

]]> Barbara Christopher 1 1286537947 2010-10-08 11:39:07 1475891571 2016-10-08 01:52:51 0 0 event 2004-08-13T11:15:00-04:00 2004-08-13T01:00:00-04:00 2004-08-13T01:00:00-04:00 2004-08-13 15:15:00 2004-08-13 05:00:00 2004-08-13 05:00:00 2004-08-13T11:15:00-04:00 2004-08-13T01:00:00-04:00 America/New_York America/New_York datetime 2004-08-13 11:15:00 2004-08-13 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Thesis Defense :: Reverse Logistics and Environmental Considerations in Equipment Leasing and Asset Management]]> 27279 Today many business enterprises employ capital assets in the form of electronic equipment (e.g., personal computers, workstations and
peripherals) in large quantities. In the face of rapid equipment changes, current tax laws and disposal challenges, leasing or procurement contracts with take-back considerations are attractive for electronic equipment.

For a large electronic equipment leasing company, optimal management of assets supported by good logistics decisions is crucial and may provide a significant competitive advantage. The leasing company tries to maximize operating profits through key decisions associated with the length of leases, efficient utilization of logistics facilities for material flow to and from customer sites, and equipment reuse, refurbishment and disposal actions.

In this research, a mixed integer linear programming (MILP) model is developed to facilitate better decisions from the perspective of an electronic equipment leasing company. A case study with representative industry data validates the approach and demonstrates the utility of the model in answering key research questions. Next, important problem uncertainties are identified and prioritized. The effects of these key uncertainties on optimal lease length and product flow decisions are examined in detail via an extended case study. It is also shown how the leasing company can make near-robust leasing decisions in the face of these uncertainties.

The computational research results also have implications for policy formulation on electronic waste. The important insights include an understanding of the potential impacts and expected effectiveness of alternative environmental legislation in different geographic areas, and the imposition of negative externalities on other policy realms as a result of this non-uniform approach. Therefore, this research contributes new models and understanding to the intersection of the fields of reverse logistics and equipment replacement, and provides valuable insights to both business asset managers and environmental policy makers.

]]> Barbara Christopher 1 1286537942 2010-10-08 11:39:02 1475891571 2016-10-08 01:52:51 0 0 event 2004-11-03T15:30:00-05:00 2004-11-03T00:00:00-05:00 2004-11-03T00:00:00-05:00 2004-11-03 20:30:00 2004-11-03 05:00:00 2004-11-03 05:00:00 2004-11-03T15:30:00-05:00 2004-11-03T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-03 03:30:00 2004-11-03 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[STATISTICS SEMINAR :: Independent Particle Filters]]> 27279 Sequential Monte Carlo methods, especially the particle filter (PF) and its various modifications, have been used effectively in dealing with stochastic dynamic systems. The standard PF samples the current state through the underlying state dynamics, then uses current observation to evaluate the samples' importance weight. However, in many applications the current observation provides significant information about the current state while the state dynamics is weak. Sampling using the current observation in this case often produces efficient samples. In this paper, we formulate the framework for a new variant of the particle filter, the independent particle filter (IPF). It generates exchangeable samples of the current state from a sampling distribution that is conditionally independent of the previous states, a special case of which uses only the current observation. Each sample can then be matched with multiple samples of the previous states for evaluating the importance weight. We present some theoretical results showing that this strategy improves efficiency of estimation as well as reduces resampling frequency in many situations. We also discuss some extensions of the IPF. Several synthetic examples and one real example are used to demonstrate the effectiveness of the method.

]]> Barbara Christopher 1 1286537946 2010-10-08 11:39:06 1475891571 2016-10-08 01:52:51 0 0 event 2004-08-24T13:00:00-04:00 2004-08-24T01:00:00-04:00 2004-08-24T01:00:00-04:00 2004-08-24 17:00:00 2004-08-24 05:00:00 2004-08-24 05:00:00 2004-08-24T13:00:00-04:00 2004-08-24T01:00:00-04:00 America/New_York America/New_York datetime 2004-08-24 01:00:00 2004-08-24 01:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[THESIS DEFENSE :: Ranking and Selection Procedures for Bernoulli and Multinomial Data]]> 27279 Ranking and Selection procedures have been designed to select the best
system from a number of alternatives, where the best system is defined by
the given problem. The primary focus of this thesis is on experiments where
the data are from simulated systems. In simulation ranking and selection
procedures, four classes of comparison problems are typically encountered.
We focus on two of them: Bernoulli and multinomial selection. Therefore, we
wish to select the best system from a number of simulated alternatives where
the best system is defined as either the one with the largest probability of
success (Bernoulli selection) or the one with the greatest probability of
being the best performer (multinomial selection). We focus on procedures
that are sequential and use an indifference-zone formulation wherein the
user specifies the smallest practical difference he wishes to detect between
the best system and other contenders.

We apply fully sequential procedures due to Kim and Nelson (2004) to
Bernoulli data for terminating simulations, employing common random numbers.
We find that significant savings in total observations can be realized for
two to five systems when we wish to detect small differences between
competing systems. We also study the multinomial selection problem. We offer
a Monte Carlo simulation of the Bechhofer and Kulkarni (1984) MBK
multinomial procedure and provide extended tables of results. In addition,
we introduce a multi-factor extension of the MBK procedure. This procedure
allows for multiple independent factors of interest to be tested
simultaneously from one data source (e.g., one person will answer multiple
independent surveys) with significant savings in total observations compared
to the factors being tested in independent experiments (each survey is run
with separate focus groups and results are combined after the experiment).
Another multi-factor multinomial procedure is also introduced, which is an
extension to the MBG procedure due to Bechhofer and Goldsman (1985, 1986).
This procedure performs better that any other procedure to date for the
multi-factor multinomial selection problem and should always be used
whenever table values for the truncation point are available.

]]> Barbara Christopher 1 1286537942 2010-10-08 11:39:02 1475891567 2016-10-08 01:52:47 0 0 event 2004-11-05T10:00:00-05:00 2004-11-05T00:00:00-05:00 2004-11-05T00:00:00-05:00 2004-11-05 15:00:00 2004-11-05 05:00:00 2004-11-05 05:00:00 2004-11-05T10:00:00-05:00 2004-11-05T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-05 10:00:00 2004-11-05 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[SEMINAR :: Examining the Cost-Effectiveness of Pharmacogenomic Strategies to Individualize Care for Cancer Patients]]> 27279 The broad availability of genetic information arising from the Human Genome Project promises to bring new modalities for testing and treatment to oncology. Advances in cancer cell biology and genetics now permit the detection of individuals with hereditary predisposition to disease, the development of gene-based drug therapies, and the individualization of drug therapy based on a patient's genetics. Pharmacogenomics refers to a spectrum of approaches to explore the association of genetic variation at any locus with drug activity or toxicity. In contrast to most drugs outside of oncology, anticancer drugs are often customized based on individual patient characteristics, such as a patient's body surface area. Despite this individualized dosing, there is great heterogeneity in the ways that patients respond to medications, in terms of both toxicity and treatment efficacy. Thus, drug dosage and selection are adjusted modified once therapy has begun based on the severity of ensuing drug toxicities and efficacy. Genetic polymorphisms in drug-metabolizing enzymes, transporters, and receptors, and in cancer cells may explain some of the inter-individual differences in the efficacy and toxicity of chemotherapy, and suggest the need for individualized therapy based on genetic information. However, the economic implications of pharmacogenomic testing prior to administering chemotherapy remain unclear. We have investigated the general principles underlying the potential for pharmacogenomic treatment strategies to become cost-effective, and are examining the cost-effectiveness particular pharmacogenetic and pharmacogenomic interventions. I will discuss a Markov model that examines the cost-effectiveness of screening children with acute lymphoblastic leukemia (ALL) for thiopurine methyltransferase (TPMT) deficiency prior to instituting 2.5 years of maintenance therapy with 6-mercaptopurine (6-MP). Children with TPMT deficiency (0.3% US population) treated with 6-MP experience severe bone marrow suppression and may die, but a simple, prospective dose reduction can prevent this effect. The model was used to compare the costs and quality-adjusted survival for children managed with pharmacogenomic testing versus those receiving conventionally-dosed 6-MP. I will also describe studies to assess the incremental cost-effectiveness of DPD genotyping prior to initiation of 5-FU therapy and UGT1A1 genotyping prior to initiation of irinotecan therapy for patients with colorectal cancer, and related work in oncology informatics to link utility-based measures of outcome to an existing database containing clinical, administrative, pharmacy, and genetic data. This enhanced database will facilitate future cost-utility studies of pharmacogenomics.

References Bala MV, Zarkin GA. Pharmacogenomics and the evolution of healthcare : is it time for cost-effectiveness analysis at the individual level? Pharmacoeconomics. 2004;22(8):495-8. Flowers CR, Veenstra D. The role of cost-effectiveness analysis in the era of pharmacogenomics. Pharmacoeconomics. 2004;22(8):481-93. Danzon P, Towse A. The economics of gene therapy and of pharmacogenetics. Value Health. 2002 Jan-Feb;5(1):5-13.

Dr. Christopher Flowers, MD, is an Assistant Professor in Hematology and Oncology and the Clinical Director for Oncology Informatics Program at the Winship Cancer Institute, Emory University School of Medicine

]]> Barbara Christopher 1 1286537941 2010-10-08 11:39:01 1475891567 2016-10-08 01:52:47 0 0 event 2004-11-11T15:00:00-05:00 2004-11-11T00:00:00-05:00 2004-11-11T00:00:00-05:00 2004-11-11 20:00:00 2004-11-11 05:00:00 2004-11-11 05:00:00 2004-11-11T15:00:00-05:00 2004-11-11T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-11 03:00:00 2004-11-11 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Collaborative Procurement and Due Date Management in Supply Chains]]> 27279 In this thesis we analyze the procurement process of buyers and
supply decisions of manufacturers. Companies are looking for ways
to decrease their procurement costs, which account for a large
percentage of the supply chain costs. We study the effects of
demand aggregation and collaborative procurement on buyers'
profitability. First, we make a high-level analysis and consider a
market with multiple buyers and suppliers where multi-unit
transactions for multiple items take place. The procurement costs
are effected by economies of scale in the suppliers' production
costs and by economies of scope in transportation. We design buyer
strategies that model different collaboration levels and assess
the role of collaboration under varying market conditions. Next,
we analyze the procurement process on a lower level and identify
benefits of inter-firm collaboration among buyers who are
potential competitors in the end market. We adopt a game-theoretic
approach to explore the economics of the basic mechanism
underlying collaborative procurement, and determine the conditions
that makes it beneficial to the participants.

Besides low procurement costs, important considerations in
supplier selection are responsiveness and the reliability of the
suppliers in meeting demand. Hence, manufacturers face the
pressure for quoting short and reliable lead-times. We cover
several aspects of the manufacturer's problem, such as quoting
reliable due-dates based on the workload status in the system,
maximizing profit considering the lateness cost incurred due to
late deliveries, and deciding on the level of inventory to
increase responsiveness. We employ a model where demand arrival
and manufacturing processes are stochastic, and obtain insights on
the optimal due-date policy and on the optimal inventory level.

]]> Barbara Christopher 1 1286537941 2010-10-08 11:39:01 1475891567 2016-10-08 01:52:47 0 0 event 2004-11-16T10:00:00-05:00 2004-11-16T00:00:00-05:00 2004-11-16T00:00:00-05:00 2004-11-16 15:00:00 2004-11-16 05:00:00 2004-11-16 05:00:00 2004-11-16T10:00:00-05:00 2004-11-16T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-16 10:00:00 2004-11-16 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Operational control of stochastic processing networks]]> 27279 A processing network is a system that takes materials of various kinds as inputs, and uses processing resources to produce other materials as outputs. A wide range of real world, complex systems can be represented within this conceptual framework, including semiconductor wafer fabrication facilities, networks of data switches, and large-scale call centers. In a manufacturing context, the processing network paradigm is flexible enough to accommodate machine-operator interactions, material handling equipment, machine breakdown, and assembly-disassembly operations. It can be used to model call centers with cross-trained operators, to model input-queued data switches, and to model congestion-based routing of road traffic. Key performance measures of a stochastic processing network include throughput (the rate at which jobs or materials flow through the system) and cycle time (the total amount of time that inputs spend in the network). Elements of an operational policy may include input control, sequencing, routing, and decisions related to batching and setups; the choice of such a policy can dramatically affect network performance.

In this talk, it will first be shown that even in simple networks, commonly used operational policies like first-in-first-out sequencing may perform badly, failing to achieve even "throughput optimality." We then present two families policies, called discrete-proportional-processor-sharing and maximum pressure policies, that are always throughput optimal, regardless of the processing network's topology or parameter values. These policies have other attractive features as well, including distributed implementation that uses only local or semi-local congestion information. A simulation study has been undertaken that evaluates these policies in a wafer fabrication setting, using SEMATECH data sets. The results of that study will be discussed, along with other attractive theoretical properties of the two policy families.

]]> Barbara Christopher 1 1286537941 2010-10-08 11:39:01 1475891567 2016-10-08 01:52:47 0 0 event 2004-11-16T11:00:00-05:00 2004-11-16T00:00:00-05:00 2004-11-16T00:00:00-05:00 2004-11-16 16:00:00 2004-11-16 05:00:00 2004-11-16 05:00:00 2004-11-16T11:00:00-05:00 2004-11-16T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-16 11:00:00 2004-11-16 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Estimation Techniques for Nonlinear Functions of the Steady-State Mean in Computer Simulation]]> 27279 A simulation study consists of several steps such as data collection, coding and verification, model validation, experimental design, output data analysis, and implementation. Our research will concentrate on output data analysis. In this field, many researchers have studied how to construct confidence intervals for the mean u of a stationary stochastic process. However, the estimation of the value of a nonlinear function f(u) has not received a lot of attention in the simulation literature. Towards this goal, a batch-means-based methodology was proposed by Munoz and Glynn (1997). Their approach did not consider consistent estimators for the variance of the point estimator for f(u). This thesis, however, will consider consistent variance estimation techniques to construct confidence intervals for f(u). Specifically, we use methods based on the techniques of nonoverlapping batch means (NBM), standardized time series (STS), and a combination of both. Our approaches are tested on moving average, autoregressive, and M/M/1 queueing processes. The results show that our new confidence interval estimators (CIEs) perform as well as or better than the CIEs based on the method of Munoz and Glynn in terms of coverage, the mean of the CI half-width, and the variance of the CI half-width.

]]> Barbara Christopher 1 1286537941 2010-10-08 11:39:01 1475891567 2016-10-08 01:52:47 0 0 event 2004-11-16T13:30:00-05:00 2004-11-16T00:00:00-05:00 2004-11-16T00:00:00-05:00 2004-11-16 18:30:00 2004-11-16 05:00:00 2004-11-16 05:00:00 2004-11-16T13:30:00-05:00 2004-11-16T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-16 01:30:00 2004-11-16 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Energy Research: Opportunities and Challenges]]> 27279 The purpose of this talk will be to present a broad overview of the Energy Quantitative Research effort at Citadel Investment Group, and highlight some challenges facing the practical application of finance theory to
energy investing. Energy markets present a unique opportunity for
financial analysis, since the underlying commodity economics cause many traditional finance assumptions to be violated. Instead, practical research solutions must address the fundamental economics and account for the shortcomings of established equity and fixed income theory. During
this talk, we will attempt to highlight some of these issues and provide a discussion framework for application of textbook theory to the trading desk reality. Further, this talk will present a brief description of the
overall hedge fund environment in which a research professional must
operate.

Founded in 1990, Citadel Investment Group is a world leader in alternative investments, with a team of over 800 people in five offices worldwide. Our research philosophy is to apply a systematic process driven approach
to investing in order to advance the reliability and repeatability of high risk adjusted returns.

Speaker Bio:

Dr. Byrns is the Director of Energy Research at Citadel Investment Group in Chicago, IL. He received his PhD in Engineering, (GA Tech 1991), as
well as a MS in Economics (GA Tech 1991), a MSE in Aerospace Engineering (GA Tech 1988) and a BSE in Mechanical and Aerospace Engineering (Princeton 1985). He has been actively involved in commodity research for almost 8 years, holding various staff and management positions at Williams
Energy, Merchant Energy Group of the Americas, and Koch Industries. Prior to entering the commodity field, he worked as a consultant in Washington
D.C.

]]> Barbara Christopher 1 1286537941 2010-10-08 11:39:01 1475891567 2016-10-08 01:52:47 0 0 event 2004-11-17T11:00:00-05:00 2004-11-17T00:00:00-05:00 2004-11-17T00:00:00-05:00 2004-11-17 16:00:00 2004-11-17 05:00:00 2004-11-17 05:00:00 2004-11-17T11:00:00-05:00 2004-11-17T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-17 11:00:00 2004-11-17 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Statistics Seminar:: Overlapping Overlapping Variance Estimators for Simulations]]> 27279 We introduce new estimators for the variance parameter of a steady-state simulation output
process. The new estimators are linear combinations of estimators formed from overlapped
versions of standardized time series and/or batch means estimators using different batch sizes.
These "overlapping overlapping" estimators have both lower bias and variance than their original
overlapping (without linear combinations) counterparts. The work is joint with Tuba Aktaran.

]]> Barbara Christopher 1 1286537941 2010-10-08 11:39:01 1475891567 2016-10-08 01:52:47 0 0 event 2004-11-17T13:00:00-05:00 2004-11-17T00:00:00-05:00 2004-11-17T00:00:00-05:00 2004-11-17 18:00:00 2004-11-17 05:00:00 2004-11-17 05:00:00 2004-11-17T13:00:00-05:00 2004-11-17T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-17 01:00:00 2004-11-17 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Pricing Path-Dependent Derivative Securities Using Monte Carlo Simulation & Intra-Market Statistical Trading Model]]> 27279 This thesis is composed of two parts. The first parts deals with a
technique for pricing American-style contingent options. The
second part details a statistical arbitrage model using
statistical process control approaches.

We propose a novel simulation approach for pricing American-style
contingent claims. We develop an adaptive policy search algorithm
for obtaining the optimal policy in exercising an American-style
option. The option price is first obtained by estimating the
optimal option exercising policy and then evaluating the option
with the estimated policy through simulation. Both high-biased and
low-biased estimators of the option price are obtained. We show
that the proposed algorithm leads to convergence to the true
optimal policy with probability one. This policy search algorithm
requires little knowledge about the structure of the optimal
policy and can be naturally implemented using parallel computing
methods. As illustrative examples, computational results on
pricing regular American options and American-Asian options are
reported and they indicate that our algorithm is faster than
certain alternative American option pricing algorithms reported in
the literature.

Secondly, we investigate arbitrage opportunities arising from
continuous monitoring of the price difference of highly correlated
assets. By differentiating between two assets, we can separate
common macroeconomic factors that influence the asset price
movements from an idiosyncratic condition that can be monitored
very closely by itself. Since price movements are in line with
macroeconomic conditions such as interest rates and economic
cycles, we can easily see out of the normal behaviors on the price
changes. We apply a statistical process control approach for
monitoring time series with the serially correlated data. We use
various variance estimators to set up and establish trading
strategy thresholds.

]]> Barbara Christopher 1 1286537941 2010-10-08 11:39:01 1475891567 2016-10-08 01:52:47 0 0 event 2004-11-17T15:30:00-05:00 2004-11-17T00:00:00-05:00 2004-11-17T00:00:00-05:00 2004-11-17 20:30:00 2004-11-17 05:00:00 2004-11-17 05:00:00 2004-11-17T15:30:00-05:00 2004-11-17T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-17 03:30:00 2004-11-17 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Evaluating the Capability and Cost of a Mass Vaccination Clinic via Computer Simulation]]> 27279 Dr. Michael L. Washington earned his B.S. in Industrial and Systems
Engineering from the University of Florida, and his M.S. and Ph.D. in
Industrial Engineering from the University of South Florida. He
currently works for the Centers for Disease Control and Prevention,
National Immunization Program in Atlanta, GA. Dr. Washington has worked
on simulation projects related to urban and rural public health clinics,
emergency rooms, and warehouses. He also developed simulations of mass
vaccination/prophylaxis clinic to help local official plan for massive
bio-terrorist attacks. Additional past projects include cost analysis
of extra-vaccinating children, cost analysis of vaccine wastage, vaccine
forecasting, and complex survey analyses of vaccine acceptance. Dr.
Washington was a consultant for the World Health Organization (WHO), and
Ghana's Ministry of Health. While in Ghana, he provided consultation
expertise in data management, statistics, and geographical informational
system concerning about seven-vaccine preventable disease. He has also
consulted with WHO South East Asia Regional Office and the National
Polio Surveillance Unit (NPSU), New Delhi, India to evaluate
surveillance software, and to assist in training vaccine preventable
disease surveillance, data management, and mapping. He visited 5 out of
7 regions in India to evaluate NPSU's data managers skills, tools, and
capabilities. Because of Dr. Washington's accomplishments, the National
Engineering Week selected him as one of the top 16 young engineers in
the nation in 2003, and he was profile in USA Today and other media
outlets throughout the year. Recently, he was nominated for a Service to
America Medal for his Homeland Security efforts in creating a mass
smallpox vaccinations computer model to help local officials prepare for
a bio-terrorist attack.

]]> Barbara Christopher 1 1286537941 2010-10-08 11:39:01 1475891567 2016-10-08 01:52:47 0 0 event 2004-11-22T14:00:00-05:00 2004-11-22T00:00:00-05:00 2004-11-22T00:00:00-05:00 2004-11-22 19:00:00 2004-11-22 05:00:00 2004-11-22 05:00:00 2004-11-22T14:00:00-05:00 2004-11-22T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-22 02:00:00 2004-11-22 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[ISyE Cookie Decorating Party]]> 27279 The School of Industrial and Systems Engineering is hosting a Cookie Decorating Party, Friday, December 3. The party will be held on the first floor (Student Lounge) of the ISyE Main Bldg., from 11:30am - 1:30pm.

]]> Barbara Christopher 1 1286537941 2010-10-08 11:39:01 1475891567 2016-10-08 01:52:47 0 0 event 2004-12-03T11:30:00-05:00 2004-12-03T00:00:00-05:00 2004-12-03T00:00:00-05:00 2004-12-03 16:30:00 2004-12-03 05:00:00 2004-12-03 05:00:00 2004-12-03T11:30:00-05:00 2004-12-03T00:00:00-05:00 America/New_York America/New_York datetime 2004-12-03 11:30:00 2004-12-03 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Minimizing Multi-zone Orders in the Correlated Storage Assignment Problem]]> 27279 In the correlated storage assignment problem, products are assigned to
storage/pick zones in a warehouse to minimize picking effort. Unlike
previous work which has focused on minimizing travel distance, our
objective is to minimize the number of zones that must be visited to fill
the orders. This problem is NP-Complete so heuristic methods are developed
to find solutions. We present a Lagrangian relaxation approach as well as
several other construction heuristics. Improvement methods discussed
include 2-exchanges and cyclic exchanges. We also consider problem
variations such as different product sizes, stock splitting, and
rewarehousing. Computational results are presented for problems containing
up to 10664 products and 40 zones. In particular, our results show that
cyclic exchanges are very powerful and can be used to obtain solutions 15%
better than those from using popularity, a standard approach.

]]> Barbara Christopher 1 1286537940 2010-10-08 11:39:00 1475891567 2016-10-08 01:52:47 0 0 event 2004-12-03T13:00:00-05:00 2004-12-03T00:00:00-05:00 2004-12-03T00:00:00-05:00 2004-12-03 18:00:00 2004-12-03 05:00:00 2004-12-03 05:00:00 2004-12-03T13:00:00-05:00 2004-12-03T00:00:00-05:00 America/New_York America/New_York datetime 2004-12-03 01:00:00 2004-12-03 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[Data Mining in Tree-Based Models and Large-Scale Contingency Tables]]> 27279 During the last decade, data mining has received great attention
from various fields. This thesis investigates data mining problems
in tree-based models and large-scale contingency tables. The first
half of the thesis pertains to the tree-based models for the
classification problem, which have been very popular in various
fields because of their interpretability and flexibility. Tree
modeling involves two major steps: tree growing and tree pruning.
Tree growing searches over the whole data set to find the
splitting point that leads to the greatest improvement in a
specified score function. Once the trees are grown, tree pruning
pursues the right sized tree that provides the best estimate of
error when the tree is applied to unseen data. In this thesis, we
propose a novel algorithm for tree pruning, called frontier-based
tree pruning (FBP). The new method has an order of computational
complexity comparable to cost-complexity pruning (CCP). Regarding
tree pruning, FBP provides a full spectrum of information: namely,
(1) given the value of the penalization parameter $lambda$, it
gives the decision tree specified by the complexity-penalization
approach; (2) given the size of a decision tree, it provides the
range of the penalization parameter $lambda$, within which the
complexity-penalization approach renders this tree size; and (3)
it finds the tree sizes that are {it inadmissible},
--- so regardless of what the value of the penalty parameter is, the
resulting tree, based on a complexity-penalization framework, will
never have these sizes. Simulations on real data sets reveal
surprising results: in the complexity-penalization approach, most
of the tree sizes are inadmissible. FBP facilitates a more
faithful implementation of cross validation (CV), which is favored
by simulations. As an extension of the FBP algorithm, we study how
CV performs in tree-based models. Considering the abundant results
available on applying CV to regression models, there is little
research on the effects of CV in classification models due to
their nonlinear structure. The main purpose of this study is to
explore the behavior of CV in tree-based models. We report
simulation studies that compare a cross-validated tree classifier
with an oracle classifier that is ideally derived on the knowledge
of underlying distributions. The main observation of this study
indicates that the difference between the testing and training
error from a cross-validated tree classifier and an oracle
classifier empirically has a linear regression relation. The
``slope'' and the ``$R^2$'' of regression models are employed as
the performance measures of a cross-validated tree classifier.
Moreover, simulation reveals that the performance of a
cross-validated tree classifier depends on the geometry, the
parameters of the underlying distributions, and the sample sizes.
Such observations can explain and justify the behavior of CV in
tree-based models.

The second half of the thesis presents multiple testing in
large-scale contingency tables and its application to pattern
recognition of protein structures. One of the most common test
procedures using two-way contingency tables is the test of
independence between two categorizations. Current significant
tests such as $chi^2$ or likelihood ratio tests provide overall
independency but bring limited information about the nature of the
association in the contingency tables. The main purpose of this
study is to develop a follow-up method to $chi^2$ or likelihood
ratio tests that identifies the significantly associated
individual cells in the contingency table. We propose a framework
of multiple testing procedures for testing independence of the
cell categories in contingency tables. In the simulation study, we
compare the power, type I error, and false discovery rate of five
different testing procedures in the contingency table. We observe
that no single procedure is superior for every scenario examined.
In addition, we record the relationships among the proportion of
true null hypotheses, power, type I error, and false discovery
rate. Finally, we employ the proposed method to identify the
patterns of pair-wise associations between amino acids involved in
$beta$-sheet bridges of proteins. We identify a number of amino
acid pairs that exhibit either strong or weak association. These
patterns provide useful information for algorithms that predict
secondary and tertiary structures of proteins.

]]> Barbara Christopher 1 1286537940 2010-10-08 11:39:00 1475891567 2016-10-08 01:52:47 0 0 event 2004-12-03T14:30:00-05:00 2004-12-03T00:00:00-05:00 2004-12-03T00:00:00-05:00 2004-12-03 19:30:00 2004-12-03 05:00:00 2004-12-03 05:00:00 2004-12-03T14:30:00-05:00 2004-12-03T00:00:00-05:00 America/New_York America/New_York datetime 2004-12-03 02:30:00 2004-12-03 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[STOCHASTICS SEMINAR :: Dynamic Due Date Quotation for Base-Stock Inventory Systems]]> 27279 Faced by squeezed profit margins due to competition, firms are
looking for ways to differentiate themselves, such as by being
responsive in fulfilling demand while keeping the delivery promises.
We look at the dynamic due date quotation problem under base-stock
inventory holding, where the demand is lead-time sensitive and unmet
due dates are penalized. We examine several facets of the due date
quotation problem, including quoting reliable due-dates based on workload
status, maximizing profit considering the lateness cost incurred
due to late deliveries, and deciding on the level of inventory. We develop
a structural analysis of the optimal due-date quotation policy under
a given base-stock level and we show an optimal policy exists and
is monotone in the number of customers. We also obtain insights on
the optimal base-stock level. We conduct experiments to identify when is
it more profitable to operate in a pure make-to-order environment,
and when is it more profitable to keep inventory; how much inventory
should be kept; and how utilization levels affect the profits.

]]> Barbara Christopher 1 1286537940 2010-10-08 11:39:00 1475891567 2016-10-08 01:52:47 0 0 event 2004-12-08T16:00:00-05:00 2004-12-08T00:00:00-05:00 2004-12-08T00:00:00-05:00 2004-12-08 21:00:00 2004-12-08 05:00:00 2004-12-08 05:00:00 2004-12-08T16:00:00-05:00 2004-12-08T00:00:00-05:00 America/New_York America/New_York datetime 2004-12-08 04:00:00 2004-12-08 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>
<![CDATA[THESIS DEFENSE :: Multivariate Quality Control Using Loss-Scaled Principal Components]]> 27279 Quality control is commonly divided into off-line activities, synonymous
with robust design (RD), and on-line procedures, also known as statistical
process control (SPC). Most research in both areas of quality control has
dealt with single variables. Since most complex systems are multivariate
in nature, there is an increasing need for user friendly multivariate
techniques.

The multivariate quadratic loss function (MQL) is a popular multivariate
technique in static RD and has occasionally been applied to multivariate
SPC. In both areas we integrate the contents of the MQL into specially
constructed principal components called loss-scaled principal components
(LSPC). We examine how well a subset of these LSPC approximate the
expected value of MQL and apply them to a RD problem featuring six
responses and eight predictor variables. We also show when
LSPCs can quickly detect and accurately diagnose shifts in location and
dispersion in multivariate SPC.

]]> Barbara Christopher 1 1286537942 2010-10-08 11:39:02 1475891567 2016-10-08 01:52:47 0 0 event 2004-11-04T11:00:00-05:00 2004-11-04T00:00:00-05:00 2004-11-04T00:00:00-05:00 2004-11-04 16:00:00 2004-11-04 05:00:00 2004-11-04 05:00:00 2004-11-04T11:00:00-05:00 2004-11-04T00:00:00-05:00 America/New_York America/New_York datetime 2004-11-04 11:00:00 2004-11-04 12:00:00 America/New_York America/New_York datetime <![CDATA[]]> Barbara Christopher
Industrial and Systems Engineering
Contact Barbara Christopher
404.385.3102]]>