Skip to main content

Selected Research Proposals

Discovery Park has launched eight integrative data science research projects as part of Purdue’s Integrative Data Science Initiative.

Tomás Díaz de la Rubia, Discovery Park’s chief scientist and executive director, launched the research focus of the data science initiative by coordinating an internal funding opportunity for ambitious proposals that apply data science to pressing, socially relevant issues.

The Request For Proposal released on March 15 resulted in 52 separate highly-competitive proposals addressing data science applications in the theme areas of Heath Care; Defense; Ethics, Society and Policy; and Fundamentals, Methods and Algorithms. The submitting proposal teams included 10 of Purdue’s colleges/schools and involved 172 Purdue faculty from 48 departments.

Investigators for selected projects: Elias Bareinboim, David Gleich, Joaquín Goñi, Sabre Kais, Jennifer Neville, Bruno Ribeiro, Audrey Ruple, Eric Waltenburg

The selected projects create synergies among researchers from across disciplines to work together and explore data science questions at the nexus of health care; defense; ethics, society and policy; and fundamentals, methods and algorithms.


Causally-Driven Healthcare Science – From Observational and Experimental Studies to Personalized and Improved Patient Outcomes

Elias Bareinboim

PI: Elias Bareinboim, Assistant Professor, Department of Computer Science, College of Science

Theme: Healthcare

Overview: Evidence generation in medicine relies on identifying the causal effectiveness of an intervention (clinical guideline, drug administration) based on randomized controlled trials (RCTs), which are expensive, time-consuming and sometimes unethical. This proposal aims to develop new methods for causal identification for evidence generation in medicine. We propose to tackle the causal generalization problem in three broad specific applications in healthcare: i) identifying causality from experimental and observational data, ii) expediting randomized controlled trials with efficient design, and iii) methods for personalized medicine.


Engineering Data Science Algorithms

PI: David Gleich, Associate Professor, Department of Computer Science, College of Science

Theme: Fundamentals

Overview: One of the recurring challenges in data science is that algorithm experts produce well-crafted software for standardized formulations of problems such as clustering and prediction, whereas everyone agrees that incorporating domain-specific insight into the formulations is critical if data science is going to achieve the expected benefit to society. Unfortunately, there is a lack of methods and frameworks to make this easy for either the algorithms experts or domain scientists. To address this problem, this proposal has an ambitious research agenda into engineering algorithms for data science. The goal of this proposal is to enable a domain scientists to express their desiderata about a data science problem through simple examples in their datasets and then automate creating a domain specific formulation. This research involves creating algorithms and methods to characterize domain-specific data with information theoretic and statistically significant properties, and then creating algorithm frameworks for the newly established properties to identify future structures.


Fingerprints of the Human Brain: A Data Science Perspective

PI: Joaquín Goñi, Assistant Professor of Industrial Engineering and Biomedical Engineering, College of Engineering

Theme: Healthcare

Overview: In the 17th century, physician Marcello Malpighi observed the existence of patterns of ridges and sweat glands on fingertips. This was a major breakthrough and originated the means to uniquely identify individuals based on fingerprints. In the modern era, the concept of fingerprinting has expanded to other sources of data such as voice recognition and retinal scans. The next challenge for human identifiability is posed on brain data, particularly on brain connectivity, as assessed through the lens of data science. The strategical aim of this proposal is to position brain research at Purdue as preeminent in innovation and to become leaders in initiatives related to individualized brain connectomics and fingerprinting.


Quantum Machine Learning for Data Analytics and Optimization

Sabre Kais

PI: Sabre Kais, Professor of Chemical Physics, Department of Computer Science, College of Science

Theme: Fundamentals

Overview: Machine-learning techniques are demonstrably powerful tools displaying remarkable success in compressing high dimensional data. These methods have been applied to a variety of fields in both science and engineering. This project will focus on “Data Science for Fundamentals, Methods and Algorithms” and will build upon Purdue’s world-leading expertise in data science, machine learning and quantum computing to tackle important real-world challenges, by developing game changing quantum algorithms to perform machine-learning tasks on large-scale scientific datasets for various industrial and technological applications based on optimization.


Formal Methods for Robust Machine Learning

Jennifer Neville

PI: Jennifer Neville, Associate Professor and Miller Family Chair of Computer Science and Statistics, College of Science

Theme: Fundamentals

Overview: While there has been a great deal of success recently in the development of machine learning (ML) methods and systems for real world applications, much of the success has been in relatively restricted domains where there is (i) a clearly defined task, with (ii) clearly defined measures of success, (iii) large amounts of labeled training examples, (iv) limited structural variation, and (v) few system constraints. This proposal takes a two-pronged approach to develop more robust and efficient ML systems by using systems engineering principles and practices to improve the deployment of ML systems, and developing foundational methodology, analysis tools, and algorithms in machine learning to enable deployment in more realistic applications


Blazing Fast Chemical Sensing

Bruno Ribeiro

PI: Bruno Ribeiro, Assistant Professor, Department of Computer Science, College of Science

Theme: Fundamentals

Overview: The field of chemical sensors is about to go through a seismic shift. Printed on top of biodegradable substrates, these revolutionary chemical sensors are designed to be short-lived, cost a few cents, and be ultra-low powered. Applications of these chemical sensors range from environmental monitoring, to precision agriculture, to health monitoring, etc. This project plans to develop hybrid data-driven and physics-driven techniques that can significantly speed up the time to get reliable sensor readings from unreliable electrical signals. If successful, our approach will result in a tool that any lay practitioner can use to automatically build new mixed data-driven and physics-driven models that give reliable chemical concentration estimates in a matter of minutes as opposed to hours.


Using the One Health Approach for Combating Antimicrobial Resistance (AMR): creating an integrated framework for the collection, analysis, and interpretation of data necessary to establish a comprehensive AMR surveillance system in Indiana

Audrey Ruple

PI: Audrey Ruple, Assistant Professor of One Health Epidemiology, College of Veterinary Medicine

Theme: Healthcare

Overview: The continued emergence and widespread occurrence of antimicrobial resistance (AMR) and multi-drug resistant microorganisms (MDRO) is a global health crisis that threatens both human and animal health. Development and spread of AMR is a complex phenomenon involving the One Health interface – overlapping interactions among humans, animals, and the environment. In order to best understand these interactions an integrated approach to monitoring must be utilized. This proposal develops a One Health AMR data platform and surveillance system to be implemented to better understand the drivers of resistance in the state of Indiana. This will allow us to utilize new approaches in an effort to prevent further increase of AMR. Once successfully implemented in the state of Indiana, this framework can be expanded to incorporate data sources from a larger geographical region.


A Relational-Based Measure of State Legislator Consequence

Eric Waltenburg

PI: Eric Waltenburg, Associate Department Head; Graduate Studies Director; Professor, Department of Political Science, College of Liberal Arts

Theme: Ethics, Society and Policy

Overview: Understanding and accurately predicting legislative outcomes is essential to the development and pursuit of public policy. Ultimately, the passage of any public law is the result of the decisions of individual legislators. This project leverages Purdue’s strengths in computer science and unstructured data analytics to build a relational database of state legislative roll call votes and derive a consequence score for individual state legislators in all 50 states. It will draw on external, internet-based data sources to test systematic explanations for the individual legislator consequence scores, and it will result in a database containing historical records of state legislators’ online activity annotated by policy frame, issue area, legislator stance or position, ideology, and other attributes.

Purdue University, 610 Purdue Mall, West Lafayette, IN 47907, (765) 494-4600

© 2019 Purdue University | An equal access/equal opportunity university | Copyright Complaints

Trouble with this page? Disability-related accessibility issue? Please contact us at datascience@purdue.edu.