Interdisciplinary Data Exploration and Analytics Lab

Discover how IDEAL is advancing data-driven discovery at CIT.

Social:

About IDEAL

The Interdisciplinary Data Exploration and Analytics Lab is a research lab dedicated to advancing data-driven discovery across a broad range of domains, including healthcare, cybersecurity, bioinformatics, and social computing. IDEAL develops and applies state-of-the-art techniques in artificial intelligence, data science, and machine learning to address complex interdisciplinary problems that cannot be solved within the boundaries of a single field. The lab brings together researchers from diverse backgrounds and actively collaborates with academic partners across the United States and Europe. Through funded projects and cross-disciplinary partnerships, IDEAL aims to translate methodological innovation into real-world impact while fostering a collaborative research ecosystem that bridges theory, data, and application.

A colorful logo featuring a light bulb with gears, a DNA strand, and a laboratory flask, labeled "IDEAL Lab."

Mission

IDEAL’s mission is to advance interdisciplinary, data-driven research while educating and mentoring future data scientists and machine learning engineers. The lab emphasizes strong technical foundations in AI, data science, and machine learning, paired with applied research experience across domains including healthcare, security, bioinformatics, and social computing. By engaging students in collaborative, grant-supported, and internationally connected research, IDEAL aims to develop skilled researchers and practitioners equipped to address complex, real-world challenges.

IDEAL Members

Halil Bisgin
Halil Bisgin Professor of Computer Science and Graduate Program Director of Data Science, College of Innovation and Technology, The University of Michigan-Flint
bisgin@umich.edu
810-766-6823
Merve Filiz Baker

Projects and Grants

  • Ben Bryer Foundation & Research and Creative Activity Fund
    • Screening for Pheochromocytoma and Paraganglioma Using Machine Learning and Natural Language Processing (PI)
  • CIT START Grant | June 2024 – June 2025
    • Toxic Effects of Chronic Exposure to Polystyrene Microplastics on Human Small Intestinal Organoids (Co-PI)
  • CIT START Grant | February 2023 – February 2024
    • Developing Containerized Lab Modules of Machine Learning for Cybersecurity (Co-PI)
  • Research and Creative Activity Fund | June 2022 – June 2023
    • A Deep Learning Approach for Combining Nuclear Magnetic Resonance Spectroscopy and Mass Spectrometry–Based Metabolomics Data Towards Disease Prediction (PI)
  • Research and Creative Activity Fund | September 2021 – September 2022
    • Developing Defense Against Adversarial Attacks Against the Power Grid Using Machine Learning (Co-PI)
  • Google Cloud Platform Credits | September 2021 – September 2022
    • Detecting Early-Warning Signals of Market Share Loss from Locus of Customer Movements (Co-PI)
  • Propelling Original Data Science Grant | June 2021 – June 2022
    • Detecting Early-Warning Signals of Market Share Loss from Locus of Customer Movements (Co-PI)
  • EDA University Center Fund | May 2020 – September 2020
    • Development of Online Resources for Fenton Area Community Service
  • MCube Grant | January 2019 – December 2020
    • Using Social Media to Understand Public Perception of the Flint Water Crisis
  • Ben Bryer Foundation Fund | May 2018 – May 2019
    • Systematic Approach for Metabolic Panel Selection for Prediction of Intrauterine Growth Restriction (PI)
  • SHPS Internal Funding | Fall 2017
    • Objective Quantification of Activity and Physiological Recovery Following Sports-Related Concussion (Co-PI)
  • Ben Bryer Foundation Fund | January 2017 – January 2018
    • A Novel Method for Identifying Drug–Drug Interactions and Its Application to a Big Data Case (PI)