Falls are a major source of injury and loss of independence among older adults, yet current fall-risk assessments are often limited to clinical settings and may not fully capture the neurological, cognitive, and motor factors that contribute to falls. This project aims to develop practical, portable methods for assessing and mitigating fall risk in elderly seniors by analyzing physiological and behavioral data collected from high- and low-fall-risk cohorts ages 70-90. Using smartphone-based tools developed in Dr. Richard Fletcher’s group, we will examine signals such as EEG, fNIRS, heart rate, balance, and motor coordination to identify measurable biomarkers associated with fall risk. Statistical analysis and machine learning methods will be used to compare risk groups, build predictive models, and support the development of accessible screening tools. In addition, the project will explore hand-motor and coordination exercises as potential low-cost interventions to improve balance, coordination, and safety in older adults.

I am interested in participating in SuperUROP because I want to deepen my experience applying engineering and computational methods to clinically meaningful problems. I am especially drawn to this project because fall risk in elderly adults can affect independence, mobility, and quality of life, making it an important area where research can have a direct human impact. This project also aligns with my broader interest in serving vulnerable populations through both research and community-oriented work.