UMass Computer Scientist Receives Research Award

AMHERST — Computer scientist Benjamin Marlin of UMass Amherst recently received a five-year, $536,527 National Science Foundation Faculty Early Career Development (CAREER) award to develop machine-learning-based tools for analyzing complex, large-scale clinical and mobile health (mHealth) data.

Marlin’s project, “Machine Learning for Complex Health Data Analytics,” is designed to help health researchers handle what he calls a data revolution. “Electronic health records are seeing wide adoption across the United States, and we’re starting to see the emergence of large stores of complex clinical data as a result,” said Marlin. “There’s significant interest in leveraging these data to enhance all kinds of clinical decision support tools with the hope that they can ultimately improve quality of care.”

Marlin’s research will also explore ways to analyze data from emerging mHealth wearable sensor systems that collect large volumes of continuous physiological measurements like respiration and electrocardiogram signals. “Developing models and algorithms that can accurately and reliably detect activities like smoking from wearable sensor data has tremendous potential for use in behavioral-science research as well as continuous health monitoring,” he noted.

The challenge with analyzing data from these sources is that they exhibit a number of complicating factors, such as sparse and irregular sampling, incompleteness, noise, between-subjects variability, high volume, high velocity, heterogeneity and non-stationarity.

“We’re not dealing with nice, clean data in these areas,” Marlin said. “The data are noisy. Parts are missing due to sensors disconnecting or clinicians not recording measurements. A number of these issues can break current data-analysis methods. The goal of this work is to design new machine-learning-based data analysis tools that are significantly more robust and accurate.”

Marlin, an assistant professor who is co-founder and co-director of the UMass Amherst Machine Learning for Data Science Laboratory, will collaborate with computer scientists, clinicians, and medical researchers at UMass Amherst, the University of Memphis, Yale University School of Medicine, and Children’s Hospital Los Angeles, who are providing access to unique mHealth and clinical data.

Marlin’s CAREER award, which will begin Sept. 1, will also extend beyond research. “An important goal of the program is to integrate education and research,” he said. He is developing a new applied-machine-learning course for the growing number of master’s students enrolling in the UMass Amherst School of Computer Science. His work will also include community education outreach through the Girls Inc. Eureka! summer program.

Before coming to UMass Amherst in 2011, Marlin was a fellow of the Pacific Institute for the Mathematical Sciences and the Killam Trusts in the Laboratory for Computational Intelligence at the University of British Columbia. He is also a 2013 Yahoo! Faculty Research Engagement Award recipient.