e-HAIL

Widely used AI tool for early sepsis detection may be cribbing doctors’ suspicions

When using only data collected before patients with sepsis received treatments or medical tests, the model’s accuracy was no better than a coin toss.

Hearing emotion: Redefining mental health monitoring via voice-based mood detection

Researchers at U-M have received a $3.6 million NIH grant to support their development of new digital phenotyping tools to better detect and measure symptoms of bipolar disorder via audio monitoring.

Clinicians could be fooled by biased AI, despite explanations

Regulators pinned their hopes on clinicians being able to spot flaws in explanations of an AI model's logic, but a study suggests this isn't a safe approach.

CSE researchers present new findings and tech at UIST 2023

CSE researchers have 2 papers and 4 demos appearing at the conference, covering new tech that improves accessibility, enhances user experience, and helps surgeons-in-training.

Dhruv Jain receives NIH grant to improve health education for people with sensory disabilities

Prof. Jain and his collaborators in Michigan Medicine will develop best practices to increase health literacy and access to information for patients with disabilities.

Nikola Banovic receives NSF CAREER Award to advance explainable AI

Prof. Banovic aims to use human-AI interaction to explain and justify AI decisions to end users.

New apps for visually impaired users provide virtual labels for controls and a way to explore images

With VizLens, users can touch buttons while their phones read out the labels, and Image Explorer provides a workaround for bad or missing alt text

With language models on the rise, how can Natural Language Processing be used for good?

A research team led by Prof. Rada Mihalcea and PhD student Zhijing Jin has created a method for identifying and categorizing research that uses NLP to address social problems.

Dhruv Jain named Google Scholar to design accessible technologies for deaf and hard of hearing people

Jain is working to design next-generation accessible technologies to give DHH people better awareness of their surroundings.

Seven papers by CSE researchers presented at CHI 2023

30 University of Michigan researchers authored and co-authored papers spanning surveillance, virtual reality, algorithmic stigma, assistive technology, and sensing systems.

Jenna Wiens receives U-M Sarah Goddard Power Award for outstanding research and advocacy for women in academia

The award recognizes U-M faculty and staff who have significantly contributed to the betterment of current challenges faced by women.

Prof. Emily Mower Provost receives NSF grant for research in personalized emotion recognition

The project aims to create new and personalized speech emotion recognition approaches and to use these approaches to investigate how changes in emotion are related to changes in mental health.

Six new projects funded by LG AI Research  

The projects are a part of LG’s mission to advance AI such as Deep Reinforcement Learning, 3D Scene Understanding, and Reasoning with a Large-scale Language Model and Bias & Fairness related to AI ethics.

Rada Mihalcea receives Distinguished Faculty Achievement Award

Mihalcea is being recognized for her contributions to computational linguistics and her efforts to broaden participation in the field of computer science.

Paper by U-M researchers selected for Best Paper in IEEE Transactions on Affective Computing

The research on automatic speech emotion recognition is one of the five papers featured in the collection.

Rada Mihalcea named new council member for CRA Computing Community Consortium

Mihalcea has been appointed as one of six new members on the Council, which works to catalyze computing research activity. Her term begins July 1.

Paper recognized for lasting impact on natural language processing

AAAI recognized Prof. Rada Mihalcea's 2006 paper which devised a way to semantically compare short texts.

$1.1M grant supports learning more about early Alzheimer's with machine learning

Data from patient records could provide a valuable historical perspective on which factors increase Alzheimer's risk.

AI-powered interviewer provides guided reflection exercises during COVID-19 pandemic