Full title: Collaborative Research: Advancing STEM Online Learning by Augmenting Accessibility with Interactive Companionship

Videos are a popular option for online learning, and captions are essential for accessibility. Two types of captions exist: typical closed captions and explanatory captions. Closed captions…

Many digital archival collections are limited due to factors such as privacy concerns and copyright. AEOLIAN combines innovative AI methods and the knowledge of scholars from multiple cultural institutions to address the accessibility of these collections, ultimately making them more accessible. Additionally, the project aims to foster collaboration amongst scholars and practitioners from…

This project brings together researchers in AI and agriculture, combining their expertise to promote advances in agriculture through AI. AIFARMS mission is to use core AI research areas such as computer vision, machine learning, data science, soft object manipulation, and intuitive human-robot interaction to address major challenges in agriculture:

• Sustainable intensification…

This project aims improve upon a tool clinicians, researchers, and systematic reviewers use to retrieve biomedical articles from bibliographic databases. Associate Professors Halil Kilicoglu and Jodi Schneider will work with Affiliate Professor Neil Smalheiser, professor of psychiatry at the University of Illinois Chicago, on the project, which has received funding from the National Institutes…

The scientific challenge for this project is to accelerate discovery and exploration of the synthetic biology design space. In particular, many parts used in synthetic biology come from or are initially tested in a simple bacteria, E. coli, but many potential applications in energy, agriculture, materials, and health require either different bacteria or higher level organisms (yeast for…

This project investigates the problem of information integrity, that is, identifying faulty or ungrounded information online. It focuses on a specific domain, that of information produced during the COVID-19 pandemic, and processes both text and image data. While significant efforts in artificial intelligence (AI) and machine learning (ML) have addressed information integrity in this type of…

Full title: CHS: Small: DeepCrowd: A Crowd-assisted Deep Learning-based Disaster Scene Assessment System with Active Human-AI Interactions

This project addresses the application of AI to disaster scene assessment (DSA). AI currently has limited success with DSA; this project…

This joint effort with Arizona State University’s CAOE team aims to create a suite of effective and efficient AI tools for analyzing cartel smuggling activities, building upon the team’s expertise in machine learning, data mining, and visual analytics.

Human papillomavirus (HPV) is the most common sexually transmitted infection in the U.S., with over 34,000 new HPV-related cancers diagnosed annually, according to the Centers for Disease Control and Prevention. An HPV vaccine, which was approved by the Food and Drug Administration (FDA) in 2006, is recommended as part of routine vaccinations for school-aged children. However, the vaccine's…

With support from the Environmental Chemical Sciences Program of the NSF Division of Chemistry, the researchers will develop machine learning models to predict the reactivity of thousands of organic contaminants (OCs) in engineered (water) and natural (soil and sediment) environments. To assess and mitigate risks associated with this vast number of OCs, accurate predictive models are needed to…

This project will assist researchers and journals in evaluating citation behavior in biomedical publications. While citations play a fundamental role in the diffusion of scientific knowledge and assessment of research on a topic, they are often inaccurate (e.g., citation of nonexistent findings, inappropriate interpretation). This inaccuracy undermines the integrity of scientific literature…

Infectious airborne pathogens and their spread have caused increased incidences of outbreaks and pandemics, which challenge our society with severe impacts on public health, economies, and social well-being. Controlling airborne pathogens is challenging because they are transmitted easily via respiratory aerosols, spread quickly over large distances, and can mutate to become more infectious…

This project will focus on real-world problems where underrepresented, rare (abnormal) examples play critical roles, such as defective silicon wafers resulting from a new semiconductor manufacturing process and rare but severe complications (e.g., kidney failure) among diabetes patients.

"This problem of explainable rare category analysis was motivated by my collaboration with IBM…

Monitoring drinking water contamination is vitally important to inform consumers about water safety, identify source water problems, and facilitate discussion of public health and the environment of our drinking water. The overall goal of this project is to develop a framework for reliable and timely detection of drinking water contamination to build sustainable and connected communities. It…

Full title: Collaborative Research: Advancing STEM Online Learning by Augmenting Accessibility with Interactive Companionship

Videos are a popular option for online learning, and captions are essential for accessibility. Two types of captions exist: typical closed captions and explanatory captions. Closed captions…

This project will study foreign influence via the lens of disinformation on news media from a computational perspective. The researchers will use Explainable Heterogeneous Adversarial Machine Learning (EXHALE) to address the limitations of current techniques in terms of comprehension, characterization, and explainability.

…

This NIH-funded project focuses on machine learning approaches for translating transdermal alcohol content (i.e., alcohol measured from a person’s skin) into blood alcohol content (“BAC”). Modern transdermal sensors are small, easy to use, and measure transdermal alcohol content frequently, but lag behind typical measures of BAC (especially breathalyzers) in terms of accuracy. This project…

Graph Neural Networks have proven to be a powerful tool for harnessing graph data, which is widely used for representing rich relational information in multiple areas. However, the performance of graph neural networks largely depends on the amount of labeled data, which is subject to an expensive and time-consuming annotation process. This creates data without labels, or a label scarcity.…