A team of students, in conjunction with Duke’s Office of Information Technology, will use of Duke’s network traffic data to perform IoT device behavioral fingerprinting that can be employed to identify device types. The data will be used to analyze trends and risks, develop security best practices, and build machine learning models that can be used to detect similar device types. Students will work directly with the network data and have access to the analytics tools used in OIT and will have a great opportunity for exploration of the data in consultation with OIT network, security and data analytics professionals.

Project Lead: Jen Vizas

Project Manager: Will Brockselsby

A team of students partnering with Duke University Libraries will explore the complicated decision space of electronic journal licensing. Electronic resources like journal articles are a major service provided by academic libraries, but the choice of what journal subscriptions to purchase can be costly and time consuming, and journal distribution companies like Elsevier manipulate their journal bundles to maximize their own profits. This team will build a model for journal purchasing by combining several years of journal usage data (including view, downloads, authorship, citations, and impact) with journal cost data. The team will work on software to improve the data cleaning and analysis process and will create visualizations and dashboards to assist the library in its decision-making efforts. Because many libraries have the same concerns about journal bundles and use the same kinds of data to make these decisions, this project may have far-reaching impacts among academic libraries.

Faculty Leads: Angela Zoss, Jeff Kosokoff

A team of students will use a variety of data sets and mapping technologies to determine a feasible location for a deep-sea memorial to the transatlantic slave trade. While scholars have studied the overall mortality of the slave trade, little is known about where these deaths occurred. New mapping technologies can begin to supply this data. Led by English professor Charlotte Sussman, in association with the Representing Migrations Humanities Lab, this team will create a new database that combines previously-disparate data and archival sources to discover where on their journeys enslaved persons died, and then to visualize these journeys. This project will employ the resources of digital technologies as well as the humanistic methods of history, literature, philosophy, and other disciplines. The project welcomes students from a broad range of disciplines: computer science; mathematics; English and literature; history; African and African American studies; philosophy; art history; visual and media studies; geography; climatology; and ocean science.

Image credit:

J.M.W. Turner, Slave Ship, 1840, Museum of Fine Arts, Boston (public domain)

Faculty Lead: Charlotte Sussman

Project Manager: Emma Davenport

The American public first encountered the term “genocide” in a Washington Post op-ed published in 1944; since then, the word’s meaning has been circulated, debated, and shaped by numerous forces, especially by words and images in newspapers. With the support of Dr. Priscilla Wald (English), a team of students led by Nora Nunn (English graduate student) and Astrid Giugni (English and ISS) will analyze how U.S. mass media—particularly newspapers—enlist text and imagery such as press photographs to portray genocide, human rights, and crimes against humanity from World War II to the present. From the Holocaust to Cambodia, from Rwanda to Myanmar, such representation has political consequences. If time allows, students will also study the representation of collective violence in Hollywood film, querying the relationship between human rights and genre. The implications of these findings could inform future coverage of human rights-related issues at home and abroad.

Faculty Leads: Nora Nunn, Astrid Giugni

A team of students led by researchers from the Michael W. Krzyzewski Human Performance Laboratory (K-Lab) will develop an analytic and report generating web-based application to help the K-Lab reduce musculoskeletal injuries in student-athletes at Duke University. This tool will produce actionable, student-athlete-specific reports that incorporate the analysis of previous injury history and current capabilities (K-Lab assessments) in order to identify injury risk and develop individualized recommendations for injury prevention. Students will develop analytic tools and scoring criteria to assess injury risk through profiling of data based on minimally clinically important differences, injury profiles, peer group analysis, and injury risk scoring strategies based on a comprehensive set of performance metrics. Injury risk identification will be furthered enhanced by clustering data analysis around joint or tissue specific injury risk, previous injury history, and athlete capabilities (strength, flexibility, and postural stability). The final deliverable will enhance injury prevention strategies for student-athletes and other populations by bridging the analytic gap between injury risk screening and actionable injury prevention strategies.

Faculty Lead: Dr. Tim Sell

Project Manager: TBD

Have you ever read or watched a movie and realized that you have seen the same story before?  How do you know if you are watching an adaptation? A team of students led by UNC-Chapel Hill graduate student Grant Glass, will develop means to track the movement of adaptations within contemporary culture through machine learning techniques. Drawing upon a variety of textual information drawn from historical and digital sources, the project team will have the opportunity to work with many different types of data. Students will identify features of different master narratives, which will be used to demonstrate how certain stories are modified and retold over and over again. By creating this training dataset, the team will use algorithms to identify adaptations in previously unidentified works. This will allow scholars to better understand at scale how certain narratives are adapted into new stories and forms.

Faculty Lead: Grant Glass

Project Manager: TBD

A team of students led by statistics professor Jie Ding from the University of Minnesota will develop algorithms to recognize human emotions (e.g. calm, happy, angry, etc.) from audio speech data, and to incorporate new emotions into an existent speech. By applying machine learning techniques to various speech datasets, students will identify features of human speech that can represent emotions, to develop software to perform emotion recognition, and to synthesize emotional speech data. Students also have the opportunity to create their own dataset, and apply their developed methods for training and testing. This work will allow further research along the direction of speech emotion analysis, and may result in new designs of human-computer interfaces.

Faculty Leads: Vahid Tarokh, Jie Ding

Project Manager: Enmao Diao

This Data Expedition seeks to introduce students to statistical analysis in the field of international development. Students construct a index of wealth/poverty based on asset holdings using four datasets collected under the umbrella of the Living Standards Measurement Survey project at the World Bank. We selected countries to represent different continents with comparable and recent survey data: Bulgaria (2007), Tajikistan (2009), Tanzania (2010-2011), and Panama (2008).

First, we construct an index of wealth based on household assets in the different countries using Principle Components Analysis. Once a poverty index is constructed, students seek to understand what the main drivers of wealth/poverty are in different countries. We include variables for health, education, age, relationship to the household head, and sex. Students then use regression analysis to identify the main drivers of poverty in different countries.

Our aim was to introduce students to the wealth of possibilities that human genotyping and sequencing hold by illustrating firsthand the power of these datasets to identify genetic relatives, using the story of the Golden State Killer’s capture with public genetic databases.

Alec Ashforth (Economics/Math), Brooke Keene (Electrical & Computer Engineering), Vincent Liu (Electrical & Computer Engineering), and Dezmanique Martin (Computer Science) spent ten weeks helping Duke’s Office of Information Technology explore the development of an “e-advisor” app that recommends co-curricular opportunities to students based on a variety of factors. The team used collaborative and content-based filtering to create a recommender-system prototype in R Shiny.

Click here to read the Executive Summary

Lucas Fagan (Computer Science/Public Policy), Caroline Wang (Computer Science/Math), and Ethan Holland (Statistics/Computer Science) spent ten weeks understanding how data science can contribute to fact-checking methodology. Training on audio data from major news stations, they adapted OpenAI methods to develop a pipeline that moves from audio data to an interface that enables users to search for claims related to other claims that had been previously investigated by fact-checking websites.

This project will continue into the academic year via Bass Connections.

Click here to read the Executive Summary.

Kimberly Calero (Public Policy/Biology/Chemistry), Alexandra Diaz (Biology/Linguistics), and Cary Shindell (Environmental Engineering) spent ten weeks analyzing and visualizing data about disparities in Social Determinants of Health. Working with data provided by the MURDOCK Study, the American Community Survey, and the Google Places API, the team built a dataset and visualization tool that will assist the MURDOCK research team in exploring health outcomes in Cabarrus County, NC.

Click here to read the Executive Summary

Nathan Liang (Psychology, Statistics), Sandra Luksic (Philosophy, Political Science),and Alexis Malone (Statistics) began their 10-week project as an open-ended exploration how women are depicted both physically and figuratively in women's magazines, seeking to consider what role magazines play in the imagined and real lives of women.

Click here to read the Executive Summary

Aaron Crouse (Divinity), Mariah Jones (Sociology), Peyton Schafer (Statistics), and Nicholas Simmons (English/Education) spent ten weeks consulting with leadership from the Parents Teacher Association at Glenn Elementary School in Durham. The team set up infrastructure for data collection and visualization that will aid the PTA in forming future strategy.

Click here to read the Executive Summary

Ashley Murray (Chemistry/Math), Brian Glucksman (Global Cultural Studies), and Michelle Gao (Statistics/Economics) spent 10 weeks analyzing how meaning and use of the work “poverty” changed in presidential documents from the 1930s to the present. The students found that American presidential rhetoric about poverty has shifted in measurable ways over time. Presidential rhetoric, however, doesn’t necessarily affect policy change. As Michelle Gao explained, “The statistical methods we used provided another more quantitative way of analyzing the text. The database had around 130,000 documents, which is pretty impossible to read one by one and get all the poverty related documents by brute force. As a result, web-scraping and word filtering provided a more efficient and systematic way of extracting all the valuable information while minimizing human errors.” Through techniques such as linear regression, machine learning, and image analysis, the team effectively analyzed large swaths of textual and visual data. This approach allowed them to zero in on significant documents for closer and more in-depth analysis, paying particular attention to documents by presidents such as Franklin Delano Roosevelt or Lyndon B. Johnson, both leaders in what LBJ famously called “The War on Poverty.”

Click Here for the Executive Summary

Tatanya Bidopia (Psychology, Global Health), Matthew Rose (Computer Science), Joyce Yoo (Public Policy/Psychology) spent ten weeks doing a data-driven investigation of the relationship between mental health training of law enforcement officers and key outcomes such as incarceration, recidivism, and referrals for treatment. They worked closely with the Crisis Intervention Team, and they used jail data provided by the Sheriff’s Office of Durham County.

Click here to read the Executive Summary

ECE majors Mitchell Parekh and Yehan (Morton) Mo, along with IIT student Nikhil Tank, spent ten weeks understanding parking behavior at Duke. They worked closely with the Parking and Transportation Office, as well as with Vice President for Administration Kyle Cavanaugh.

BME major Neel Prabhu, along with CompSci and ECE majors Virginia Cheng and Cheng Lu, spent ten weeks studying how cells from embryos of the common fruit fly move and change in shape during development. They worked with Cell-Sheet-Tracker (CST), an algorithm develped by former Data+ student Roger Zou and faculty lead Carlo Tomasi. This algorithm uses computer vision to model and track a dynamic network of cells using a deformable graph.

Weiyao Wang (Math) and Jennifer Du , along with NCCU Physics majors Jarrett Weathersby and Samuel Watson, spent ten weeks learning about how search engines often provide results which are not representative in terms of race and/or gender. Working closely with entrepreneur Winston Henderson, their goal was to understand how to frame this problem via statistical and machine-learning methodology, as well as to explore potential solutions.

Runliang Li (Math), Qiyuan Pan (Computer Science), and Lei Qian (Masters in Statistics and Economic Modelling) spent ten weeks investigating discrepancies between posted wait times and actual wait times for rides at Disney World. They worked with data provided by TouringPlans.

Building off the work of a 2016 Data+ team, Yu Chen (Economics), Peter Hase (Statistics), and Ziwei Zhao (Mathematics), spent ten weeks working closely with analytical leadership at Duke's Office of University Development. The project goal was to identify distinguishing characteristics of major alumni donors and to model their lifetime giving behavior.

Over ten weeks, Math/CompSci majors Benjamin Chesnut and Frederick Xu joined forces with International Comparative Studies major Katharyn Loweth to understand the myriad academic pathways traveled by undergraduate students at Duke. They focused on data from Mathematics and the Duke Global Health Institute, and worked closely with departmental leadership from both areas.

John Benhart (CompSci, Math) and Esko Brummel (Masters in Bioethics and Science Policy) spent ten weeks analyzing current and potential scholarly collaborations within the community of Duke faculty. They worked closely with the leadership of the Scholars@Duke database.

Over ten weeks, Mathematics/Economics majors Khuong (Lucas) Do and Jason Law joined forces with Analytical Political Economy Masters student Feixiao Chen to analyze the spati-temporal distribution of birth addresses in North Carolina. The goal of the project was to understand how/whether the distributions of different demographic categories (white/black, married/unmarried, etc.) differed, and how these differences connected to a variety of socioeconomic indicators.

Graduate Student: Jacob Coleman, 3rd year Ph.D. student in Statistical Science

Faculty Instructor: Colin Rundel

Class: STA 112, Data Science

Computer Science majors Erin Taylor and Ian Frankenburg, along with Math major Eric Peshkin, spent ten weeks understanding how geometry and topology, in tandem with statistics and machine-learning, can aid in quantifying anomalous behavior in cyber-networks. The team was sponsored by Geometric Data Anaytics, Inc., and used real anonymized Netflow data provided by Duke's Information Technology Security Office.

A virtual reality system to recreate the archaeological experience using data and 3D models from the neolithic site of Çatalhöyük, in Anatolia, Turkey. 

Molly Rosenstein, an Earth and Ocean Sciences major and Tess Harper, an Environmental Science and Spanish major spent ten weeks developing interactive data applications for use in Environmental Science 101, taught by Rebecca Vidra.

The goal of this project is take a large amount of data from the Massive Open Online Courses offered by Duke professors, and produce from it a coherent and compelling data analysis challenge that might then be used for a Duke or nation-wide data analysis competition.

Ethan Levine, Annie Tang, and Brandon Ho spent ten weeks investigating whether personality traits can be used to predict how people make risky decisions. They used a large dataset collected by the lab of Prof. Scott Huettel, and were mentored by graduate students Emma Wu Dowd and Jonathan Winkle.