MENU Signal & Image Processing and Machine Learning
News Feed
GenAI diffusion models learn to generate new content more consistently than expected
Award-winning research led by Prof. Qing Qu discovered an intriguing phenomenon that diffusion models consistently produce nearly identical content starting from the same noise input, regardless of model architectures or training procedures.Linking online and offline social networks to better predict real world impact
Prof. Lei Ying leads a new MURI that is focused on the interplay between online and offline networks and how they could impact disruptive behavior and events.Improving generative AI models for real-world medical imaging
Professors Liyue Shen, Qing Qu, and Jeff Fessler are working to develop efficient diffusion models for a variety of practical scientific and medical applications.Neural Collapse research seeks to advance mathematical understanding of deep learning
Led by Prof. Qing Qu, the project could influence the application of deep learning in areas such as machine learning, optimization, signal and image processing, and computer vision.Improving the accuracy and applicability of large language models, like ChatGPT
Prof. Al Hero’s new method, which enhances the reliability of predictive models and promises to reduce the risk of AI hallucinations, was selected as a spotlight paper at NeurIPS 2023.Understanding attention in large language models
How do chatbots based on the transformer architecture decide what to pay attention to in a conversation? They’ve made their own machine learning algorithms to tell them.A coaching bot for students learning coding, computational Machine Learning, and AI
Prof. Raj Rao Nadakuditi is developing a generative AI coaching bot that provides feedback to strengthen self-regulated learning skills.Research describing quantum-inspired computational imaging earns impact award
This Q&A with award co-recipient Alfred Hero offers a glimpse into the emerging field of single photon imaging.Research to simplify big data graphs earns Best Paper Award at IEEE SSP 2023
Research by PhD student Neophytos Charalambides and Professor Alfred Hero addresses computational and storage bottlenecks for graphs used in statistical problems, signal processing, large networks, combinatorial optimization, and data analysis.Nanobiotics: AI for discovering where and how nanoparticles bind with proteins
A new tool in the fight against superbugs goes beyond protein folding simulations like AlphaFold, potentially revealing antibiotic candidates.A brain game may predict your risk of infection
When a person's cognitive function is highly variable, they're likely to be more infectious and have more symptoms after exposure to a respiratory virus.Miniature and durable spectrometer for wearable applications
A team led by P.C. Ku and Qing Qu have developed a miniature, paper-thin spectrometer measuring 0.16mm2 that can also withstand harsh environments.Neophytos Charalambides receives Best Poster Award for research in the area of Data Science
The research can be applied to a wide range of big data applications that rely on the multiplication of two matrices in linear algebra.Designing Synthetic Human Gut Microbiome with AI
Prof. Al Hero was interviewed and gave a presentation about his research using machine learning to improve our understanding of the human gutIn Digital Signal Processing, students experiment with sensors for creative projects
Students created everything from a Wordle helper to a tool for melanoma detection to a program that identifies different marine species based on their underwater song.Teaching Machine Learning in ECE
With new courses at the UG and graduate level, ECE is delivering state-of-the-art instruction in machine learning for students in ECE, and across the UniversityQing Qu receives CAREER award to explore the foundations of machine learning and data science
His research develops computational methods for learning succinct representations from high-dimensional data.Katie Bouman talks legacy of the black hole imaging project and favorite U-M memories
Before Bouman became the face of the project that brought us the first ever image of a black hole, she was wowing ECE professors with design projects and hoarding Domino’s pizza with her HKN family.New grant aims to create better algorithms to manage big data by getting “non-real”
Professors Laura Balzano and Hessam Mahdavifar are developing new ways to compress data through randomized algorithms to remove redundancies$20M NSF AI-EDGE Institute aims to transform 5G and beyond networks
University of Michigan is a core member of a new NSF-led Institute that is a collaboration between 11 institutions, three government research labs, and four global companiesThree teams of graduate students awarded prizes for their final projects in Image Processing (EECS 556)
KLA sponsored prizes for three outstanding projects focused on improving image processing for neurosurgery and satellite applications and MRI reconstruction techniques.
3D motion tracking system could streamline vision for autonomous tech
Transparent optical sensor arrays combine with a specialized neural network in new University of Michigan prototype
Prof. Qing Qu uses data and machine learning to optimize the world
A new faculty member at Michigan, Qu’s research has applications in imaging sciences, scientific discovery, healthcare, and more.
Caroline Crockett awarded Rackham Predoctoral Fellowship for research bridging two fields
Crockett’s dissertation will integrate two fields: image processing & machine learning and engineering education research
Research to improve medical imaging of the brain receives Magna cum Laude Merit award
The interdisciplinary team was able to dramatically speed up the process while potentially doubling the quality of the image
Magna cum Laude Merit Award for research to detect the progress of diseases such as multiple sclerosis
The researchers’ imaging technique is fast, accurate, and reproducible
Melissa Haskell receives NIH Fellowship for research to improve brain imaging
ECE postdoc Melissa Haskell works on improving functional magnetic resonance imaging so we can better measure and understand brain activity.
Catching nuclear smugglers: fast algorithm could enable cost-effective detectors at borders
The algorithm can pick out weak signals from nuclear weapons materials, hidden in ordinary radiation sources like fertilizer.
Live public street cams are tracking social distancing
Voxel51, a U-M startup led by Prof. Jason Corso, uses custom AI to continuously track vehicle, cyclist, and pedestrian traffic in real time at some of the most visited places in the world.
Could a smartwatch identify an infection before you start spreading it?
A wrist-worn device detected disrupted sleep 24 hours before study participants began shedding flu viruses.
Alfred Hero named Fellow of Society for Industrial and Applied Mathematics (SIAM)
Hero was elected "for contributions to the mathematical foundations of signal processing and data science."
Using machine learning to detect disease before symptoms manifest
Prof. Alfred Hero speaks to ECE about his work using data to predict the transmission of infectious disease among people who are pre-symptomatic or asymptomatic and how it relates to COVID-19.A 3D camera for safer autonomy and advanced biomedical imaging
Researchers demonstrated the use of stacked, transparent graphene photodetectors combined with image processing algorithms to produce 3D images and range detection.
Creating a place where kids of all abilities can play together
Prof. Hun-Seok Kim helped design iGYM, an augmented reality system that allows disabled and able-bodied people to play physical games together.
Machine Learning and Systems: A conversation with 2020 Field Award winners Al Hero and Anders Lindquist
Hero and Lindquist took a few minutes to talk about the impact of machine learning on Signal Processing and Control Systems, and what they plan to do about it
Beyond Apollo 11: U-M ECE’s role in advancing space exploration
For the 50th anniversary of the Apollo 11 moon landing, U-M ECE takes a look back – and a look forward – to how our professors, students, and alums have made their mark on the field.
Alfred Hero Receives 2020 IEEE Fourier Award
Hero’s research in signal processing has explored theoretical foundations and applications including personalized health imaging and information networks.
Laura Balzano aims to improve precision medicine as a Fulbright Scholar
Balzano will work with Portuguese researcher Mário Figueiredo to develop new machine learning methods impacting medical diagnosis and treatment.
Laura Balzano receives NSF CAREER Award to improve machine learning for big data applications
Her research deciphering messy data sets will first tackle applications in genetics and computer vision.
Laura Balzano receives ARO Young Investigator Award to improve high-dimensional big data problems
Applications include managing large networked systems, such as sensor networks, power grids, or computer networks.
ECE and data science: a natural connection
Electrical and Computer Engineering (ECE) faculty and students at Michigan are part of the revolution in data science that is happening today.
Prof. Laura Balzano receives AFOSR Young Investigator Award for research that addresses massive streaming data
Balzano uses statistical signal processing, matrix factorization, and optimization to unravel dynamic and messy data.
Laura Balzano partners with 3M to advance research in big data
Prof. Laura Balzano received a 2018 3M Non-Tenured Faculty Award to advance her research in Big Data.Students win prizes for improving image processing techniques for liver cancer detection and much more
Students in EECS 556: Image Processing, explore methods to improve image processing in applications such as biomedical imaging and video and image compression
Improving communication between humans and robots in 20 noisy questions
Hero and his team may have discovered a better way to facilitate communication using a twist on the classic game of 20 Questions.
Alfred Hero illustrates common threads of complex networks in Distinguished University Professor lecture
Lecture part of highest professorial honor bestowed on U-M faculty.
Seeing through materials
By developing a fast algorithm to map out the paths light takes through yogurt, researchers aim to someday see through skin.
Students in EECS 556 win prizes for improving image processing techniques for camera motion blur and facial recognition
These students are learning to improve images in medical imaging, and improve facial recognition
Student teams earn prizes for analog-digital converter circuit designs in EECS 511
The winning projects were designed for battery-operated mobile applications as well as instrumentation and measure applications.
Gopal Nataraj receives U-M Rackham Predoctoral Fellowship to support high-impact research in medical imaging
Award for outstanding doctoral candidates near the end of their study.
COVE: a tool for advancing progress in computer vision
Centralizing available data in the intelligent systems community through a COmputer Vision Exchange for Data, Annotations and Tools, called COVE.
Alfred O. Hero, III named John H. Holland Distinguished University Professor of EECS
Hero is honored for his extraordinary accomplishments that have brought distinction to himself, his students, and to the entire University.A better 3D camera with clear, graphene light detectors
While 3D films are currently made using multiple cameras to reconstruct each frame, this new type of camera could record in 3D on its own.
Al Hero gets a shoutout from the court
Hero was recognized as part of a program that sheds light on the University’s most distinguished faculty.
Al Hero receives 2015 IEEE Signal Processing Society Award
This is the highest award given by the Signal Processing Society, and honors outstanding technical contributions in the field.
Jeff Fessler receives Distinguished Faculty Achievement Award
Prof. Fessler has revolutionized medical imaging with groundbreaking mathematical models and algorithms that improve both safety and quality.
Laura Balzano receives Intel Early Career Faculty Honor Program Award for research in big data
The purpose of the ECFHP is to help Intel connect with the best and brightest early career faculty members who show great promise.
Using data science to achieve ultra-low dose CT image reconstruction
Ultra-low dose CT scans that provide superior image quality could not only benefit patients, but they could open up entirely new clinical applications.
Prize winning class team project for improved image processing
The project entails investigating a recent paper and both reproducing and extending the research.
Yelin Kim wins Best Student Paper Award at ACM Multimedia 2014 for research in facial emotion recognition
She computationally measures, represents, and analyzes human behavior data to illuminate fundamental human behavior and emotion perception, and develop natural human-machine interfaces.
Prof. Raj Nadakuditi awarded DARPA Young Faculty Award for research that could help reveal the brain’s secrets
His research will impact the ability to investigate the structure of brain circuits through the use of optical imaging techniques.
Fighting lung cancer: Faster image processing for low-radiation CT scans
This advance could be important for fighting lung cancers, as symptoms often appear too late for effective treatment.
Chia-Hsiang Chen awarded Intel PhD Fellowship
Chia-Hsiang’s research focuses on designing low-power and error-resilient circuit techniques for digital signal processing applications.
Student Spotlight: Nick Asendorf – Matrix Musician
Nick specializes in the area of machine learning and statistical signal processing.
Research in machine learning earns Notable Paper Award at AISTATS 2014
Prof. Scott’s research is in the field of machine learning, and his paper builds upon “supervised pattern classification.”
Hao Sun earns 3 Paper Awards for medical imaging research
Hao’s research is focused on improving the quality of images from magnetic resonance imaging pulse design.
Mai Le receives CoE Distinguished Leadership Award
Mai has served as Community Service Co-chair of the Graduate Society of Women Engineers since arriving at Michigan in 2011.
Student Spotlight: Mai Le – Finding a better way to diagnose breast cancer with MRI
The research group is using statistical signal processing to create crisper images with only 20% of the data required by a traditional MRI scan.
David Hong awarded NSF Graduate Research Fellowship
Hong intends to apply machine learning and signal processing techniques to the massive data sets now available to researchers.
Gopal Nataraj earns Best Paper Award for improving MRI
Nataraj is using big data techniques to transform the field of medical imaging
Gopal Nataraj receives ISA Fellowship to support research that will improve MRIs
Nataraj’s research aims to generate higher-quality and faster MRI images, resulting in improved diagnostics of neurological disorders and autoimmune diseases.
Zhaoshi Meng receives Best Paper Award at CAMSAP 2013
This work will provide a way to efficiently reveal relationships between even distant entities in a network.
Al Hero named 2013 IEEE SPS Technical Achievement Award Winner
Prof. Hero is an internationally recognized expert in the field of signal and image processing.
Pin-Yu Chen receives Rackham Chia-Lun Lo Fellowship
Chen’s work can be used in community detection in social networks, network vulnerability assessment in communication systems, and more.
Jeff Fessler receives 2013 IEEE Edward J. Hoffman Medical Imaging Scientist Award
This award recognizes outstanding contributions to the field of medical imaging science.
Research that will lead to sharper photos earns best paper award
The method they developed compares favorably with the best of current techniques, while being faster and easier.
Jae Young Park receives Best Student Paper Award for research impacting structural health monitoring
SHM systems are critical for monitoring aging structures and infrastructure in a cost-effective manner.
Research in distributed networks earns Notable Paper Award at AISTATS
The research provides a way to efficiently reveal relationships between even distant entities in a network.
Predicting your risk of illness
Imagine a future when you could predict whether or not you are at risk of becoming sick.
New technology allows CT scans to be done with a fraction of the conventional radiation dose
“We’re excited to be adding Veo to the measures we already have in place to ensure that we get diagnostic images using the lowest amount of radiation possible.”
Breakthrough: Researchers find wide gap in immune responses of people who did or didnt get the flu after exposure
If scientists can understand what happens at the genome level that makes people more or less susceptible to viral illness, they could potentially develop therapies to prevent illness.
New techniques in medical informatics lead to improved diagnosis of MDS
The technique involves a visualization method that renders clinical flow cytometry data more interpretable to pathologists.
Gyemin Lee receives Best Paper Award for research in machine learning for biomedical diagnosis
Lee’s primary motivation is to apply his research methods to hematopathology, the study of blood-related diseases.
U-M researchers win 2010 Signal Processing Best Paper Award
The work, published in 2006, will be acknowledged at the EUSIPCO Conference in Denmark.
Prof. Al Hero receives 2009 Signal Processing Magazine Best Paper Award
The paper addresses the importance of knowing where networks of sensors are located once they’ve been deployed.
Prof. Clay Scott Receives CAREER Award for Research in Signal Processing
Yong Long receives Best Poster Award for work in medical imaging
Long’s work describes a new algorithm for performing model-based methods in a way that requires less computation yet provides improved image quality.