UC San Diego

Advances in technology have resulted in the use of sensors in a great variety of applications ranging from weather forecasting, GPS tracking to physical activity measurement. Novel analytic techniques are being developed to study these densely sampled data. My research projects focus on approaches to analyze and model accelerometry data. Accelerometers measure minute-level human movement, and hence provide a rich framework for assessing physical activity patterns of an individual. Using accelerometer data collected in research studies in the School of Medicine at the University of California San Diego, our objectives are (a) to ascertain activity patterns incorporating temporal and subject-to-subject variation (b) to test if these patterns are associated with health outcomes such as obesity, cancer status, biomarkers and quality of life. We apply modern machine learning techniques and develop novel mathematical frameworks to analyze these big data. We anticipate that this work will provide statistical and computational tools to study accelerometry and inform societal guidelines on leading a healthy lifestyle.