The CITRIS Core Seed Funding program supports nascent ideas in information technology led by University of California researchers, spurring the ingenuity of UC innovators to respond to emerging research topics and societal issues. Through interdisciplinary collaborations, seed funds foster growth across the CITRIS campuses and jumpstart society’s next tech solution. Seed funds are designed to support the groundwork, data collection and prototyping needed to pursue larger awards that address major unsolved challenges in the IT sector. Prior awardees have attracted significant funding from federal, state, private and philanthropic sources.
SAFETY GUARANTEES IN THE CONTEXT OF GENERATIVE ARTIFICIAL INTELLIGENCE MODELS
Principal Investigator/s:
Ayush Pandey (lead PI, UC Merced),
Gireeja Ranade (UC Berkeley)
Air traffic control is a safety-critical service — meaning a single malfunction or mistake may lead to severe property damage, serious injury or death. It is also a very complicated system, simultaneously incorporating voice communication between pilots and traffic controllers, radar and meteorological data, and information about flight plans and maintenance logs. Generative AI has the potential to enhance the efficiency of air traffic control by managing various manual tasks and automatically detecting anomalies. However, generative AI is susceptible to user-interface attacks and is also prone to “hallucinating,” or offering reasonable-sounding but incorrect responses. This project aims to explore whether techniques from control theory can be used to provide safety guarantees for generative AI systems. The research team will identify a publicly available large language model and curate a dataset from the existing Federal Aviation Administration (FAA) catalog to use as an experimental testbed.
ACTIVITY MONITORING TO IMPROVE CAREGIVER CONNECTION AND CARE FOR OLDER ADULTS LIVING ALONE WITH ALZHEIMER’S DISEASE
Principal Investigator/s:
Alyssa Weakley (Lead PI, UC Davis Health),
Shijia Pan (UC Merced),
Hao-Chuan Wang (UC Davis Health)
Alzheimer’s disease is expected to affect 1 in 9 people over the age of 65 in the United States by 2050. Many patients with dementia currently live alone, and the number of people who take on remote caregiving responsibilities will steadily increase in coming years. Family members who provide care from a distance often must balance these duties with their roles as parents and employees, increasing their stress in a situation already rife with challenges. This project intends to create a cohesive digital platform to help long-distance caregivers monitor their loved ones’ everyday activities, such as eating, cleaning and taking medication, and to communicate with them about the data. The technology will use vibration sensors and machine learning to detect deviations from regular behavior and will provide an interactive data visualization and communication tool, with the ultimate goal of keeping family members with dementia safely in their homes and preventing expensive and burdensome crisis-driven care.
RESTORING SPEECH COMMUNICATION WITH A MULTIMODAL DECODER-SYNTHESIZER
Principal Investigator/s:
Lee Miller (Lead PI, UC Davis),
Daniel J. Cates (UC Davis Health),
Ahmed Sabbir Arif (UC Merced)
More than 1 in 100 people worldwide have lost their ability to produce natural and comprehensible speech — a condition called dysarthria — due to cancer, stroke or another cause. Right now, there is no technology to truly restore speech, only a few inadequate workarounds. This project will develop an assistive device that combines recordings of a person’s facial expressions and muscle movements and uses neural networks to synthesize and produce fluent speech in their own voice. The user will be able to move their mouth silently, as if they were speaking, to activate the device and generate their voice. This decoder-synthesizer will help restore quality of life for the tens of millions of individuals with dysarthria, allowing them to more easily and effectively interact with their co-workers, friends and loved ones.
THE IMPACT OF SHARED VALUES AND POWER ON SUCCESSFUL MENTORING FOR UNDER-REPRESENTED MINORITIES IN STEM
Principal Investigator/s:
Sarah McCullough (UC Davis),
Erin Hestir (UC Merced),
Anita Balaraman (UC Berkeley)
A chasm often lies between what is taught in the classroom and what students need to be successful. Mentorship provides a vehicle for raising greater expectations by students and gauging whether a student is prepared to be successful in post-graduate academic endeavors or in the world of work. Unfortunately, mentorship remains a hidden pedagogy in undergraduate and graduate education, and beyond. This project aims to study the characteristics of mentoring programs that benefit historically underrepresented minorities in STEM and increase their retention and continuation in STEM fields. The program will study the impact of a digital mentorship program, enabling mentees to gain professional development skills and garner career advice during COVID-19 given social distancing requirements and across geographic barriers. This work will be presented at the University of New Mexico Mentoring Institute conference in Oct. 2022.
PLATFORMS AND THE FUTURE OF WORK IN DIGITIZED AGRICULTURE
Principal Investigator/s:
Martin Kenney (UC Davis),
M. Anne Visser (UC Davis),
John Zysman (UC Berkeley),
Catherine Keske (UC Merced)
As intelligent tools and systems are adopted in agriculture, California agriculturalists and workers will need to adapt and adjust. Data sharing can be used to create value by increasing transparency, traceability, and productivity. These benefits are predicated upon platform adoption. The conundrum is that, as the intermediary, the platform owner acquires significant power. This research examines five forms of platform organization and their benefits and drawbacks for actors in the agri-food system, farmers in particular. The types discussed are 1) startups, 2) agro-food industry firms, 3) agricultural cooperatives, 4) specially formed consortia of agri-food system actors, and 5) internet companies such as Google. The project will analyze the business models for each, assess likelihood of adoption, and effect on farmers and their practices.
DATA-DRIVEN FALL PREVENTION AND INTERVENTION FOR OLDER ADULTS
Principal Investigator/s:
JoAnn Seibles(UC Davis Health),
Wan Du (UC Merced),
Shijia Pan (UC Merced)
Preventing falls among older adults is an important issue for these individuals, as well as their families and caregivers. Although organizations have started offering fall-prevention programs, participation remains low. For example, over the last 10 years, participation in the Healthy Aging Association’s (HAA) Young-At-Heart (YAH) balance training in Stanislaus County, CA, has increased at a lower rate than the increase of its senior population. This project will design, implement, and test a system using Internet of Things (IoT) technology that can assess the fall risk of older adults by passively measuring a set of fall risk factors. The performance of the system will be validated in HAA YAH classes. The research findings are important for improving the well-being of older adults and reduce the social cost of fall treatments.
AUTOMATIC BUILDING FAULT DETECTION AND DIAGNOSTIC SYSTEM USING SMARTPHONES
Principal Investigator/s:
Alberto Cerpa (UC Merced),
Avideh Zakhor (UC Berkeley)
Researchers will build a smartphone app whereby commercial-of-the-shelf (COTS) sensors are added to a mobile phone that can be used by facilities’ crews to detect and diagnose problems.