Jun 12
0

Rosiana Natalie

By |

I have a strong research interest in the intersection of Artificial Intelligence (AI), Human-Computer Interaction, and Accessibility. My research centers on developing human-AI interactive systems to improve video accessibility for blind and low-vision (BLV) individuals. Audio Descriptions (AD) provide a verbal narration of on-screen actions, objects, and settings, allowing BLV individuals to enjoy videos without seeing the visuals. Leveraging advancements in AI, specifically in computer vision and natural language processing, I aim to enhance AD for both traditional and immersive formats, such as 360° videos. My work also seeks to streamline the AD creation process and accommodate individual viewer preferences when consuming AD. Thus, these efforts broaden accessibility and interactivity in digital media.

  • Science Mentor: Anhong Guo, Information; Electrical Engineering and Computer Science, College of Engineering
  • Research Theme: Methodology / Healthcare
Jun 12
0

Mohna Chakraborty

By |

The goal of my research is to examine the real-world usage of GenAI techniques and develop approaches to improve the skills needed in LLMs to handle social situations and enable the explainability, interpretability, replicability, and overall robustness of LLMs in handling social situations.

  • Science Mentor: David Jurgens, Information; Electrical Engineering and Computer Science, College of Engineering
  • Research Theme: Methodology / Social Science
Jun 27
0

Jeremy Seeman

By |

Data Science Fellow Alum, Michigan Institute for Data Science

Research Associate, Urban Institute; Adjunct Research Assistant Professor, ICPSR, University of Michigan

I’m broadly interested in understanding how public data curators embed socially desirable values like privacy and confidentiality protections, equity, and reproducibility into their data publishing practices. My methodological research combines tools from theoretical computer science and computational social science to design and characterize complex structured errors induced by these practices. In doing so, I aim to demonstrate how these data curator interventions affect reproducible social science and evidence-based policymaking. Additionally, my qualitative research investigates the sociological and normative dimensions of how these interventions are implemented in practice; in particular, I’m interested in translational gaps between formal mathematical approaches and sociological approaches to ethics and values in data publishing, especially as applied to law and policy. My work at MIDAS continues this research in collaboration with the Inter-university Consortium for Political and Social Research (ICPSR), here at the Institute for Social Research (ISR).

  • Science Mentor: Yajuan Si, Institute for Social Research
  • Research Theme: Refining formal privacy methods and applying them to survey data.
Jun 27
0

Amirhossein Moosavi

By |

Amir will focus on how artificial intelligence can assist in medical decision-making to enhance personalized treatments and benefit patients in complex care environments. For example, he will explore the possibility of integrating structured and unstructured data into the decision-making process while considering resource scarcity and its impact on health outcomes.

  • Science Mentor: Mariel Lavieri, Industrial and Operations Engineering, College of Engineering
  • Research Theme: Using AI methods to improve optimization algorithms and incorporating personal and organizational constraints for healthcare management decision-making.
Sep 05
0
Profile picture of Bernardo Modenesi

Bernardo Modenesi

By |

The labor market is a setting increasingly disrupted by AI (both in allocation of wages and of jobs) and yet understudied in the ethical AI research space. My research agenda has been focused on the combination of unsupervised learning methods, from network theory, and discrete choice tools, in order to improve the understanding of labor market dynamics and consequently promote evidence for oversight and regulation towards labor market fairness.

AI also shapes the lives of households through mortgages. I have been also interested in exploring interpretability and fairness questions related to AI automated decisions in the mortgage industry, in partnership with the Rocket Companies. In addition to topics related to the nature of the mortgage decision algorithms, I also plan to explore the impact of mortgage decisions in opportunities in life.

Accomplishments and Awards

Aug 25
0

Elyse Thulin

By |

My research focuses on applications of computational methods to better understand human behaviors. One of my main projects applies natural language processing methods to examine interactions in an online substance use recovery group to better understand substance use recovery pathways, mental health, and social relationships.

Accomplishments and Awards

Sep 11
0
Maryam Bagherian

Maryam Bagherian

By |

My background is in applied mathematics and my primary research interest centers on developing algorithms and methodologies for data science using machine learning. More specifically, I am focused on developing algorithms for multidimensional multimodal big data which find primary application in medicine yet it is generalizable to other branches where bid data emerge. 

My current research focuses on online tensor recovery methods (i.e. complication and decomposition) using simultaneous auxiliary information. They are mainly designed for multi-omic data (e.g. spatial transcriptomic data, genomic data and etc.).

The proposed methods will have collateral benefits for the scientific community and for the diagnosticians. The former may investigate new approaches and the latter may utilize these methods with the purpose of developing online/user-friendly platforms for the end-users. 

Sep 08
0

Stephen Ajwang

By |

Stephen Ajwang is a Tutorial Fellow in the Department of Informatics and Information Science at Rongo University, Kenya, where he also received his MSc in Information Technology. He is also pursuing a PhD in Information Technology. His research interest lies in the realm of Big data analytics for climate smart agriculture.

The increasing volume of data and the availability of advanced technologies such as machine learning and big data analytics have revolutionized the way data is captured, processed, stored and mined. Accordingly, almost all facets of everyday life have applied these technologies to enhance efficiency and increase productivity through creation of seamless systems that are intuitive and capable of providing real-time, high-quality, and accessible data to facilitate decision making. It is on this basis that I intend to work on a project on Leveraging Big Data Analytics for Climate Smart Agriculture. The goal of this project is to develop a data lake and an information system which integrates analytics and machine learning to provide appropriate and accessible climate-based information.

Aug 27
0

efrén cruz cortés

By |

efrén studies the way algorithms reproduce bias and discrimination. Automated procedures are often designed to mimic the historical data humans have generated. Therefore, unintendedly, they have learned to discriminate based on class, race, gender, and other vulnerable groups. Such a phenomenon has serious consequences, as it may lead to furthering economic inequality, depriving the poor of resources, over-incarceration of people of color, etc. efrén’s goal is to understand the dynamics of the system the algorithm belongs to and assess which structural interventions are the best actions to both avoid discrimination and accomplish the desired goal for the population of interest.

Aug 19
0

Dan Li

By |

Intelligent systems behaviors, usually concealed, are almost everywhere nowadays: human-like virtual interactions, responsive financial systems, flexible traffic allocation, and more. Beneath the surface, intelligent systems encompass the developments of learning, abstraction and inference, of which large amounts of data are the core. My research focuses on developing online-data-driven approaches to support theoretical and algorithmic foundations of real-time intelligent behaviors of systems. Directions include safe planning, robust operation and as well as reliable anomaly detection.