Researchers Find Way to Predict Your Movements with GPS Data

Researchers at North Carolina State University and the Korea Advanced Institute of Science and Technology recently presented a new statistical model that simulates human mobility patterns, which could be used for infrastructure planning, public health studies of disease outbreak, and business development planning.

Presented at the 28th IEEE Conference on Computer Communications in Rio de Janeiro, Brazil, the new statistical model, which simulates the way people move over the course of a day, a month or longer, "found that people tend to perform multiple activities in clusters that are in close proximity to each other - such as going to a bank, a dry-cleaner and a pharmacy that are all located on the same street," said North Carolina State University spokesman Matt Shipman.

Approximately 100 volunteers at five locations in the U.S. and South Korea were given global positioning system (GPS) devices by the researchers at North Carolina State University and the Korea Advanced Institute of Science and Technology, who tracked the participants' movements over time.

According to Dr. Injong Rhee, a co-author of the study, by plotting the points where the study participants stopped, and their movement trajectories, researchers were able to determine patterns of mobility behavior.

Unsurprisingly, the researchers at North Carolina State University and the Korea Advanced Institute of Science and Technology found that the study participants tend to more frequently visit locations that are popular among other people.

The new model is called the Self-similar Least Action Walk (SLAW). The SLAW model suggests that people in trying to make the most efficient use of their time cluster activities together when those activates are in close physical proximity - a bank, a dry-cleaner and a pharmacy located on the same street. "This behavior creates patterns in which people make many short "jumps" within the clustered areas while making a few long jumps among the clustered areas," said North Carolina State University spokesman Matt Shipman.

By tracking the fundamental statistical properties of human mobility SLAW "could be used by civil engineers to plan roads, by public health officials to study virus outbreak spread, or by telecommunication companies for planning where to locate cell-phone towers. Any situation where you would want to be able to predict where people will go," said Dr. Injong Rhee.

"SLAW: A Mobility Model for Human Walks"

Authors: Seongik Hong, Seong Joon Kim and Injong Rhee, North Carolina State University; Kyunghan Lee and Song Chong, Korea Advanced Institute of Science and Technology

The research team that developed the model includes Rhee, NC State Ph.D. candidate Seongik Hong, NC State post-doctoral research associate Seong Joon Kim, and KAIST researchers Kyunghan Lee and Song Chong. The National Science Foundation funded the research.