Data Analytics & Information Systems

Data Analytics & Information Systems

This division brings together members from academia, industry and government who share a common interest in topics related to research and practice of data analytics and information systems. The DAIS division is primarily interested in the theory, methodology and practice in all technical areas that develop or apply to data analytics and information systems.

Research gallery

One of the benefits of belonging to a professional society is the opportunity to share knowledge about various topics of interest.

Topic: Integrating HIV and HPV: A Novel Approach with Hybrid Agent-Based and Compartmental Simulation Methods
Overview:  Ms. Xinmeng Zhao. The traditional single-disease model might lead to inaccurate estimations of an intervention's effectiveness, as it fails to consider the syndemic nature of diseases. This oversight is particularly evident in sexually transmitted diseases (STDs) like human papillomavirus (HPV) and human immunodeficiency virus (HIV), where co-infection can compromise the immune response to either virus, or shared behavioral factors influence their transmission. Recognizing these complexities and existing computational challenges, a new mixed agent-based network and compartmental (MAC) simulation framework has been developed.

Topic: ADs: Active Data-sharing for Data Quality Assurance in Advanced Manufacturing Systems
Overview: Mr. Yue Zhao. Machine learning (ML) methods are widely used in manufacturing applications, which usually require a large amount of training data. However, data collection needs extensive costs and time investments in the manufacturing system, and data scarcity commonly exists. With the development of the industrial internet of things (IIoT), data-sharing is widely enabled among multiple machines with similar functionality to augment the dataset for building ML models.

Topic: Research Overview of Systems Intelligence and Optimization Laboratory (SIOL) at Mississippi State University
Overview: Dr. Haifeng Wang and his research team have been focused on data mining and optimization solutions for health, agricultural, and manufacturing systems. The objective is to develop intelligent decision support models and theories that are robust and easily interpretable. This research faces challenges, such as real-time, large-scale, distributional shift, and uncertainty, because of the variation, dynamic, and stochastic characteristics of the practical process. Here, we discuss two current research topics to illustrate our research theme: (1) Distributionally robust unsupervised domain adaptation, (2) Towards practical clinical decision support through interpretable machine learning.

Topic: Bayesian Sparse Regression for Mixed Multi-Responses with Application to Runtime Metrics Prediction in Fog Manufacturing
Overview: Dr. Xiaoyu Chen and his collaborators focus on statistical inference methods to enable predictive computation offloading in fog manufacturing by joint modeling multivariate mixed responses which follow different types of distributions.

Topic: NP-ODE: Neural Process Aided Ordinary Differential Equations for Uncertainty Quantification of Finite Element Analysis
Overview: Dr. Yinan Wang and his research group focus engineering-driven machine learning for complex physical systems. This research overview will present one of their works on the physics-informed stochastic process for uncertainty quantification of finite element analysis. This research was awarded the Best Paper Award in the 2022 IISE Transactions with Focus Issue on Design and Manufacturing and selected as the Finalist in 2021 INFORMS Quality, Statistics and Reliability (QSR) Best Student Paper Competition.

Topic: Clustering Spatially Correlated Functional Data with Multiple Scalar Covariates
Overview: Hui Wu and her team focus on developing statistical and machine learning models for complex data (e.g., mixed-type data, functional data, insufficient information data) in industrial systems. This research overview will present one of their works on a clustering algorithm for spatially correlated functional data with covariates, followed by future research plans. This research was awarded as the best student paper in DAIS of IISE conference 2021.

Topic: An Online Approach to Covert Attack Detection and Localization in Power Systems
Overview: Dan Li, Nagi Gebraeel, Kamran Paynabar, and A.P. Sakis Meliopoulos from Georgia Tech research cybersecurity vulnerabilities in power systems and how to detect and localize covert attacks. 

Topic: Ecommerce Order Fulfillment Optimization at IBM Reserach
Overview: Dr. Xuan Lin and her team at IBM Research strive to solve challenging ecommerce analytics and optimization problems. The team have been working closely with external business customers, and have deployed multiple production solutions for ecommerce retailers.

Topic: Research Overview of Complex System Design and Analysis Laboratory
Sang Won Yoon, Assistant Professor, Systems Science and Industrial Engineering, State University of New York at Binghamton
Overview: Dr. Sang Won Yoon and his research team has been studying a variety of emerging research domains including 1) distributed decision making, coordination protocol design and collaborative control theory, 2) large-scale data analytics and predictive modeling, 3) mail-order pharmacy system design and analysis, 4) healthcare systems optimization, 5) production & manufacturing systems optimization, and 6) warehouse management and transportation. This research overview will outline a brief description of six research domains, followed by future research plans.

Topic: Visual Sensing and Data Analytics
Mehdi Khazaeli, Assistant Professor, Engineering Management, University of the Pacific
Overview: Dr. Khazaeli and his research team at UOP are working on multimedia analysis and using contextual queuing to improve segmentation, scene detection and object recognition. This research will ultimately contribute to sport biomechanics, training environment and building information modeling.

About the Division

This division brings together members concerned with the cost-effective utilization of computer technology throughout organizations. Members are involved in the interface between management and computer system design, including procurement, procedures and software selection.

See the IISE DAIS Board here.

Vision

Become the leading division in IISE by increasing networking and partnership between its members and promoting forums to engage, share and recognize innovative ideas in the field of data analytics and information systems.

Mission 

The Data Analytics and Information Systems (DAIS) Division of the Institute of Industrial and Systems Engineers (IISE) brings together members from academia, industry and government who share a common interest in topics related to the research and practice of data analytics and information systems. The DAIS division is primarily interested in the theory, methodology, and practice in all technical areas that develop or apply DAIS, including (but not limited to):

  • Network Science and Complex Systems
  • Data Analytics and Statistical Learning
  • System Informatics and Optimal Control
  • Smart and Interconnected Automation Systems
  • Machine Learning and Artificial Intelligence
  • Decision Support System
  • Grid/Cloud Computing
  • Healthcare Delivery
  • Homeland Security and Disaster Management
  • Human System Integration
  • Human Computer/Human Machine Interaction (HCI/HMI)
  • Industry 4.0
  • Information and System Security
  • Information Visualization
  • Intelligent Transportation System
  • Internet of Things (IoT)
  • Multi-agent System
  • RFID and Sensor Network
  • Robotics and Automation
  • Smart Grid
  • Smart Manufacturing
  • Ubiquitous/Pervasive System
  • Usability
  • User Experience Design

Archived Newsletters