Industrial, Manufacturing, and Systems Engineering

Dr.  Harsha Gangammanavar from the Department of Engineering Management, Information, and Systems Southern Methodist University will be presenting at an IMSE seminar Wedensday, December 5, 2018 at 1:15pm in Nedderman Hall, Room 100. Dr. Gangammanavar’s presentation title, abstract, and biographical sketch are below.

Title: Sequential Sampling-based Stochastic Optimization Algorithms For Power Systems Applications.
Author: Harsha Gangammanavar, PhD
Location: Nedderman Hall Room 100
Date: Wednesday, December 5, 2018
Time: 1:15pm

Abstract: Optimization problems arising in power systems operations have motivated numerous mathematical programming models and algorithms over many decades. The large-scale introduction of  renewable resources in recent years has called for another wave of innovations – mainly in stochastic optimization. These innovations are expected to be scalable for real-scale power systems and to address the intermittent nature of renewable resources. In order to meet such expectations,  a more effective integration of decision and data sciences is necessary. With this in mind, this talk will present a class of sequential sampling-based stochastic optimization approaches. These approaches will be presented in the context of stochastic optimization problems that arise in power systems operations including economic dispatch, estimating reserve requirements, and distributed storage control. These problems, and corresponding algorithmic developments, span both the two-stage as well as the multistage stochastic programming settings. The sequential sampling approaches allow for engineering problems in power systems to use statistical models in service of constrained optimization. Specifically, these algorithms do not rely on a-priori characterization of uncertainty through scenarios or distributions, and hence, can be used directly with data streams generated using state-of-the-art simulators. Results obtained from our computational experiments on real scale power systems will also be presented.

Biographical Sketch:  Harsha Gangammanavar is an Assistant Professor in the Engineering Management, Information, and Systems in Bobby B. Lyle School of Engineering at Southern Methodist University. Prior to joining the department, Dr. Gangammanavar was a Postdoctoral Fellow at Clemson University and a Visiting Assistant Professor at the University of Southern California. He received his M.S. in Electrical Engineering and Ph.D. in Operations Research from the Ohio State University, and B.E. degree in Electronics and Communications Engineering from Visvesvaraya Technological University in India. His research interests are in optimization under uncertainty, large-scale optimization, and their applications.

 

–Posted by Jay Rosenberger

UT Arlington faculty and graduate students from the College of Engineering and the College of Architecture, Planning and Public Affairs (CAPPA) attended and presented at the 2018 INFORMS Annual Conference, which was held November 4th to 7th in Phoenix, AZ. INFORMS is a professional association of more than 11,000 academics and practitioners in the field of operations research and the management sciences. The INFORMS Annual Meeting brings together researchers and practitioners from the United States and around the world to share the most current research and applications in the field.

IMSE faculty Dr. Victoria Chen chaired a session titled Sustainability Topics in Urban Environment. Dr. Stephen Mattingly from Civil Engineering and IMSE graduate students Alireza Fallahi, Azam Boskabadi and Shirish Rao were the speakers in the session. Dr. Jay Rosenberger organized a session Data Science in Health Care Operations Research. IMSE faculty Dr. Yuan Zhou and Dr. Aera Leboulluec contributed to this session along with Ph.D. student Amith Viswanatha and alum Dr. Gazi Md Daud Iqbal.

Dr. Atefe Makhmalbaf from CAPPA and Dr. Mohsen Shahandashti from Civil Engineering presented their talk in the session Infrastructure Systems Towards a Smart City.

As a QSR (Quality, Statistics, and Reliability) member, Dr. Chen Kan participated in the QSR 20th Anniversary Workshop. He presented his work on Network-based Analysis for Condition Monitoring of Cardiac Patients in a session called Data Analytics in Healthcare Applications, chaired by Dr. Dongping Du from Texas Tech University.

Dr. Shouyi Wang chaired a session titled Data Analytics and Modeling for Health Informatics and Decision Making. IMSE gradate students Maryam Moghimi and Rahil Hosseini and Dr. Wang contributed three talks in the session. Dr. Wang also co-chaired the 13th INFORMS Data Mining & Decision Analytics Workshop, which is a one day event with 64 accepted paper presentations worldwide and three keynote speakers on data mining and decision analytics. The IMSE alum Kinming Puk’s paper “Selection of Hierarchical Features via Sparse Group Regularization” was selected as one of the Best Paper Finalists in the workshop.

–Posted by Shirish Rao, Chen Kan, and Shouyi Wang and Edited by Jay Rosenberger

Dr.  Chen Kan from the Department of Industrial, Manufacturing, and Systems Engineering at the University of Texas at Arlington will present a Seminar this Monday, November 19, at 1:15pm in Nedderman Hall (NH) 105.  Dr. Kan’s presentation title, abstract, and biographical sketch are below.

Title: Heterogeneous Recurrence Analysis and Its

Applications on Manufacturing and Healthcare

Author: Chen Kan PhD

Location: Nedderman Hall Room 105

Date: Monday, November 19, 2018

Time: 1:15pm

Abstract: Recurrence (i.e., approximate repetitions of a certain event) is one of the most common phenomena in natural and engineering systems. Recurrence analysis has been widely used to characterize nonlinear and non stationary systems and identify dynamic transitions (e.g., change of disease conditions or manufacturing quality). However, most of the existing work focus on homogeneous recurrence variations. This talk will present a new methodology to investigate heterogeneous recurrence and link with the objectives of anomaly detection. The developed methodology will be demonstrated in both manufacturing and healthcare applications.

Biographical Sketch: Chen Kan is currently an assistant professor in the Department of Industrial, Manufacturing and Systems Engineering at UTA. He earned his PhD. in Industrial and Manufacturing Engineering from the Pennsylvania State University in 2017. His research focuses on the monitoring and anomaly detection of complex systems, with applications on advanced manufacturing and smart health.

Congratulations to IE Doctoral Student, MD Mamunur Rahman, and Dr. Yuan Zhou for their paper, “Alleviating Traffic Congestion by the Strategy of Modal Shift from Private Cars to Public Transports: A Case of Dhaka City, Bangladesh.” The Computational Social Science Society of the Americas recognized it as a “Best Paper Finalist” because it “represented the spirit, rigor, and professionalism of computational social science” during the 2018 CSS Conference, which was held at Santa Fe, New Mexico from October 25-28, 2018.

Dr.  Caroline Krejci from the Department of Industrial, Manufacturing, and Systems Engineering at the University of Texas at Arlington will present a Seminar this Monday, October 22, at 1:00pm in Nedderman Hall (NH) 105.  Dr. Krejci’s presentation title, abstract, and biographical sketch are below.

Title: Modeling Consumer Adoption Decisions in Residential Renewable Energy Systems: An Agent-based Approach

Author: Caroline Krejci, PhD

Location: Nedderman Hall Room 105

Date: Monday, October 22, 2018

Time: 1:00pm

Abstract: The electricity market in the U.S. is beginning to transition from a utility-side centralized generation-distribution model to a customer-side distributed generation model. Residential consumers have demonstrated a growing interest in solar-based electricity, which has resulted in increased adoption of distributed solar on the rooftops of owner-occupied residences over the last decade. However, increased rooftop photovoltaic (PV) adoption has reduced utility companies’ revenues, leading them to change their policies to discourage rooftop PV adoption. Furthermore, the ability to install rooftop PV systems is limited to households with sufficient income and appropriate roof structure, which has led to equity concerns among policymakers. To address these issues, a system-level approach is required. This paper describes an agent-based model that was designed to study consumer adoption behavior for different renewable energy models and the resulting impacts on stakeholder objectives. In this model, consumer agents in an urban neighborhood decide in each time-step whether they will adopt a particular renewable energy model, based on their own heterogeneous preferences and interactions with other agents. Simulation results demonstrate the interdependencies of different renewable energy programs and the value of considering multiple stakeholder objectives when designing residential renewable energy systems.

Biographical Sketch: Dr. Caroline Krejci is an Assistant Professor in the Department of Industrial, Manufacturing, and Systems Engineering at the University of Texas at Arlington.  She worked as an industrial engineer for UPS and as an operations engineer for Lutron Electronics before earning a Ph.D. in Industrial Engineering from the University of Washington in 2013.  Prior to joining UT Arlington, she was an Assistant Professor at Iowa State University.  Dr. Krejci’s research interests are focused on the development of quantitative methodologies for the analysis and management of sociotechnical systems.  She specializes in modeling supply networks as complex adaptive systems, which enables the realistic representation of network participants as autonomous and heterogeneous agents that are capable of complex planning, decision making, interactions, and adaptations in a dynamic environment.  Such complex systems often exhibit unpredictable and nonlinear behavior, which can be captured through the use of agent-based modeling techniques.  Dr. Krejci is particularly interested in using these techniques to explore the implications of different management policies on long-term social, environmental, and economic system sustainability.

–Posted by Jay Rosenberger

Dr. Richard Stone from the Department of Industrial and Manufacturing Systems Engineering at Iowa State University will be presenting at an IMSE seminar on Friday, November 2, 2018 at 1:00pm in Nedderman Hall, Room 100. Dr. Stone’s presentation title, abstract, and biographical sketch are below.

Title: Human Performance Engineering: A presentation on the use of modern technology to enhance human performance using virtual reality and exoskeletons.

Author: Richard Stone, PhD

Location: Nedderman Hall Room 100

Date: Friday, November 2, 2018

Time: 1:00pm

Abstract: This presentation will focus on the area of human performance engineering. Two studies will be presented. The first will investigate the effect of virtual reality on both cognitive and physiological learning in the welding domain. The second will focus on the domain of exoskeletons, and how this technology can be used to enhance direct performance and training among law enforcement officers. The end result of both studies was enhanced human performance via the introduction of appropriately engineered technologies.

Biographical Sketch: Richard T. Stone PhD is an Associate Professor in the Department of Industrial and Manufacturing Systems Engineering at Iowa State University. He received his Ph.D. in Industrial Engineering from the State University of New York at Buffalo in 2008. He also has an MS in Information Technology, a BS in Management Information Systems as well as university certificates in Robotics and Environmental Management Science. His current research focuses primarily in the area of human performance engineering, particularly applied biomedical, biomechanical and cognitive engineering. He focuses on the development of technologies and techniques to enhance human operations.

Aurélie Thiele from the Engineering Management, Information and Systems Department at Southern Methodist University in Dallas, Texas will present at the Seminar on Monday September 24 at at 1:15pm in Room 105 of Nedderman Hall. Dr. Thiele’s presentation title, abstract, and biographical sketch are below.

Title: Robust Portfolio Optimization with Options

Author: Aurélie Thiele

Location: Nedderman Hall (NH) Room 105

Date: Monday, September 24

Time: 1:15pm – 2:15pm

Abstract: We consider the problem of maximizing the worst-case return of a portfolio when the manager can invest in stocks as well as European options on those stocks, and the stock returns are modeled using an uncertainty-set approach, with a range forecast for each factor driving the returns and a budget of uncertainty limiting the deviations of these factors from their nominal values. While options and robust optimization have gained acceptance from the finance community and the optimization community, respectively, to mitigate the high levels of uncertainty that managers face, little attention has been spent on considering them jointly due to the computational difficulties that arise from the problem structure. We present theoretical results regarding the structure of the optimal allocation, in particular with respect to diversification, and analyze how the optimal allocation varies with increasing values of the budget of uncertainty. Our results provide insights into how the manager chooses to protect his portfolio against uncertainty based on the characteristics of the options (retail prices and strike prices), specifically, which uncertainty protection he is willing to purchase at which price. We document the performance of our approach in numerical results that compare our robust portfolio allocation to several benchmarks, showing that our approach performs very well in practice.

Joint work with Hedieh Ashrafi of Southern Methodist University.

Biographical sketch: Aurélie Thiele is an Associate Professor in the Engineering Management, Information and Systems department at Southern Methodist University in Dallas, TX. Prior to that, she spent twelve years as an Assistant Professor and tenured Associate Professor at Lehigh University in Bethlehem, PA in the department of Industrial and Systems Engineering, where she served as co-director of the Master of Science program in Analytical Finance. She holds a MS and PhD in Electrical Engineering and Computer Science from MIT and a “diplome d’ingénieur” from the Ecole des Mines de Paris in Paris, France. Her research on decision-making under high uncertainty and robust prescriptive analytics has received the George E. Nicholson prize, the IBM Faculty Award, the Lehigh Faculty Innovation Grant and multiple National Science Foundation grants, among others.