5 minute read
Big Data
Developing technologies and methodologies necessary for data-driven decision-making.
MArkerS And MileStoneS
1987 C3I Center established (precursor to C4I Center)
2004 Center for Air Transportation Systems Research founded
2013 MS in Data Analytics Engineering approved by SCHEV
Data Mining Advances Biology and Work of Clinicians
Computer science associate professor Huzefa Rangwala says one of his projects related to bioinformatics works on the same principles as Netfix: Both make recommendations based on previous behaviors.
Rangwala employs data mining to analyze the behavior of bacteria in the human body, and to look at the whole spectrum of data in disease processes, from infammatory bowel disease to obesity. The fun part, according to Rangwala, is that while he is advancing computer science, he’s also advancing biology and medicine, and the work of clinicians.
Collaborating with chemists and others, Rangwala is working with "recommended molecules," taking data mining several steps forward, and inventing new computer software solutions to discover hidden patterns.
"Data mining is not just looking for phone numbers," says Rangwala, “but exploring and discovering the unknown. It leads to many innovations in varied felds.” Rangwala's work, like many of Mason's top researchers, is cross-disciplinary. He is collaborating with Siddhartha Sikdar, associate professor of bioengineering, on a National Science Foundation-funded project to develop a prototype for a prosthetic arm. The project focuses on amputees who have no forearms, and the team is striving to develop a device that duplicates complex movements of the arm and hand. "You have muscular signature remnants in your arm," explains Rangwala, "which can be found with ultrasound probes." The aim is to replicate the patterns in muscle movements using a combination of robotics, electrical engineering, and bioengineering.
His interests are far-ranging, and he credits the graduate students and colleagues he works with, as well as his mentors, with helping him advance his work. His own mentoring, which he does with undergraduates, graduate students, and high school students, fuels his fascination with the learning process. It's a question that involves innate physical and intellectual abilities,
Huzefa Rangwala, assistant professor in the Computer Science Department, confers with Nadine Kabbani, assistant professor in molecular neuroscience, in her lab at Mason’s Krasnow Institute for Advanced Study.
cultures, and the art of teaching, and it's another research area where data mining may help people.
Rangwala’s research interests include data mining, bioinformatics, learning analytics, and high-performance computing. He was also the recipient of a long string of teaching and research awards from Mason and other institutions in recent years. His research is funded by NSF, NIH, DARPA, NRL, Google, and USDA, and includes the prestigious NSF CAREER Award.
A version of this story by Molly Brauer originally appeared on the Ofce of Research and Economic Development website.
The goal of data analytics is to make sense of massive amounts of data culled from every aspect of our lives—from shopping habits (think Netfix suggesting a movie you might like) to health statistics to crime trends to weather patterns to any number of applications—and to draw inferences or conclusions from that data to boost efciency, production, or proftability.
Big Data Provides Solutions for Airline Savings and Passenger Satisfaction
What if you didn't have to go to the airport to rebook a cancelled fight? What if you could use your smartphone to rebook before ever leaving your home or hotel? Sounds impossible? Maybe not.
Sanja Avramovic, a PhD candidate from the Volgenau School of Engineering, and associate professor Lance Sherry may have a workable solution for passengers and airlines.
Avramovic, a Serbian-born mother of a two-year-old daughter, earned a master's degree in Belgrade before coming to the United States in 2009. She chose Mason for its proximity to Washington, D.C., and the quality of its programs. Her research aimed to develop a methodology for pre-emptive rebooking of cancelled airline fights.
"I had no previous experience in aviation," says Avramovic, "but as soon as I started working on the fight simulator with Dr. Sherry, I was fascinated."
The research studied the feasibility and benefts of preemptive rebooking of passengers on cancelled airline fights by addressing some key questions. For example, what would happen if passengers were given the opportunity to choose a rebooking time prior to their ticketed departure when they know their fight is cancelled? Who would beneft? What would the savings look like? How would this improve the passenger experience?
By using massive public data sets from the Bureau of Transportation Safety, Avramovic discovered that pre-emptive re-booking is not only feasible, it is desirable. "Changes in technology and procedures have improved in airline passenger mobility," says Avramovic. "So many people are connected to the airline via email and smartphone apps in a way that they weren't years ago. This communication between airlines and passengers increases opportunities for coordination." Her research analyzed schedules, on-time performance, and load factors. Avramovic says, "Airlines know in advance if there is a large-scale event such as a snow storm. I wondered what would happen if passengers could decide what is the best for them: rebooking before or after the ticketed departure, instead of going to the airport only to fnd out their fight is cancelled and they have to wait for a later one."
She is using a methodology developed at Mason that will estimate the delays and costs on a given day. Her Monte Carlo testing engine is written in Structured Query Language (SQL), a special-purpose programming language. It allows a certain percentage of passengers to be rebooked on earlier fights when their fight is cancelled. She applied the delay and cost methodology to investigate the efects of early rebooking.
Avramovic has approached the U.S. Department of Veterans Afairs (VA) about using this methodology in other contexts. "It is very exciting to think about the massive data sets that the VA has. While the air transportation has a great deal of data, the VA has even more."
A version of this story by Martha Bushong originally appeared on the Volgenau School website.