Electrical Engineering and Computer Sciences & Civil and Environmental Engineering
Project: “Real-time Video Monitoring of Falls in Memory-Care Facilities for Individuals with Alzheimer's and Related Dementias”
The main goal of the project is to deploy an online system composed of off-the-shelf wall-mounted cameras to passively detect safety-critical events for individuals with Alzheimer’s disease and related dementias enabled by a human in the loop to assist large networks of memory care facilities. Specifically, the system will provide the following automated detection of safety-critical events: 1) Identification of when the patient has fallen down, and 2) Identification of when a patient has risen from bed.
It does not require action of individuals or their caregivers such as wearing a fall pendant and is therefore well-suited for individuals with ADRD. We develop a deep learning approach to identify and pre-filter falls not perfectly, but well enough to leave the last check to a human, who will call the facilities in case of detected safety critical event. The human can monitor several facilities at a given time.
Alex Bayen is the Liao-Cho Professor of Engineering at UC Berkeley, in the Electrical Engineering and Computer Science department. His field of expertise is mobile sensing and optimization. Prior to becoming a faculty at UC Berkeley, he worked for the Department of Defense in France where he held the rank of Major. He has a B.S. from Ecole Polytechnique, and an M.S. and Ph.D. from Stanford University. He has advised over 20 Ph.D. students and 100 undergraduate / master students. He published 2 books and over 200 publications, and has received numerous awards, including the PECASE (White House), CAREER (NSF), Ruberti Prize (IEEE) and Huber Prize (ASCE).
Pulkit Agrawal is a Ph.D. Student in the department of Computer Science at UC Berkeley and his research focuses on computer vision, robotics and computational neuroscience. Pulkit completed his bachelors in Electrical Engineering from IIT Kanpur and was awarded the Director’s Gold Medal. He is a recipient of Fulbright Science and Technology Award, Goldman Sachs Global Leadership Award, OPJEMS, Sridhar Memorial Prize and IIT Kanpur’s Academic Excellence Awards among others. His research papers have been published in top AI conferences and have received best paper awards.
Electrical Engineering and Computer Sciences
Project: "Allegro: Secure and Privacy-preserving Data Analytics”
As the growth in large-scale data collection continues, much of this valuable data remains siloed due to privacy concerns. This results in underutilization of the data, hindering advancements in many fields. The work of Dawn Song and Noah Johnson aims to address this important issue by creating a privacy-preserving data analytics and machine learning platform that enforces fine-grained security and privacy policies on sensitive data while enabling rich data analytics and machine learning. Their system is built on a novel program analysis and rewriting framework. The analysis engine determines the security and privacy impact of a program prior to its execution, and the rewriting engine automatically modifies the program to ensure compliance with the specified security policies. Their approach is practical and easy to deploy: it is transparent to data analysts without requiring any changes to their workflow, and works with all standard databases without requiring any changes to the database. The system will encourage data analytics and machine learning across a broad range of domains—including healthcare, finance, and government—while providing strong formal guarantees of privacy.
Dawn Song is a Professor in the Department of Electrical Engineering and Computer Science at UC Berkeley. She has done extensive research at the intersection of machine learning and security. She is the recipient of various awards including the MacArthur Fellowship, the Guggenheim Fellowship, the NSF CAREER Award, the Alfred P. Sloan Research Fellowship, the MIT Technology Review TR-35 Award, and Best Paper Awards at top conferences.
Noah Johnson is a fifth year Ph.D. candidate with significant experience in both industry and academic research. Noah’s research contributions have spanned several areas including binary analysis, vulnerability diagnosis, mobile security, and security and privacy for big data. He has presented his work at top-tier academic security conferences as well as Black Hat, a premiere venue for industry security practitioners.
Project: "Innovating Diagnostics and Treatment Planning for Lower Back Pain"
Professor O'Connell and her team are developing patient-specific computer models from medical images to guide surgery. By evaluating stresses place on the spine with deconstruction and realignment, they hope to allow surgeons to optimize their surgical strategies by decreasing stresses place on the spine after surgery. To do this they are working with surgeons at UC Davis Medical Center.
Grace O'Connell is an Assistant Professor in the Department of Mechanical Engineering and is a co-director of the Berkeley Biomechanics Laboratory. O'Connell's research focuses on soft tissue biomechanics, including the intervertebral disc and articular cartilage. Her research combines computational and experimental approaches to understanding the effect of injury and degeneration on tissue mechanics.
Grace is partnering with Bo Yang, a fourth year Ph.D. student in the Department of Mechanical Engineering. Yang's research is focused on developing subject-specific computational models to study disc joint mechanics.