Lopata Hall, Room 101
"DIBS: A Data Integration Benchmark Suite"
Adviser: Roger Chamberlain
As the generation of data becomes more prolific, the amount of time and resources necessary to perform analyses on these data increases. What is less understood, however, is the data preprocessing steps that must be applied before any meaningful analysis can begin. This problem of taking data in some initial form and transforming it into a desired one is known as data integration. Here, we introduce the Data Integration Benchmarking Suite (DIBS), a suite of applications that are representative of data integration workloads across many disciplines. We apply a comprehensive characterization to these applications to better understand the general behavior of data integration tasks. As a result of our benchmark suite and characterization methods, we offer insight regarding data integration tasks that will guide other researchers designing solutions in this area.
"Deep Learning to Locate Victims of Sex Trafficking"
Adviser: Sanmay Das
According to a 2016 research study interviewing victims of sex trafficking, over sixty percent of child sex trafficking survivors were at one point advertised online. These advertisements include photos of the victim often posed provocatively in a hotel room. It is imperative that law enforcement be able to quickly identify where these photos were taken in order to determine the specific locations and the geographic extent where a trafficker moves their victims. In order to determine the hotel in the photos of victims, law enforcement currently perform time consuming manual investigations; for example, they ask individuals who are regular travelers if they recognize the location photographed, and compare the photos to those on travel websites, which can often be out of date or of only the nicest rooms at a hotel with professional photography. This talk will present the dataset of hotel room photos collected by the 100,000 every day travelers who use our TraffickCam smartphone application, and discuss how that dataset, combined with innovative deep learning approaches, has allowed us to build a platform for law enforcement to efficiently locate where a victim of sex trafficking was photographed.