Research

Research projects at Rhodes iiD focus on building connections. We encourage crosspollination of ideas across disciplines, and to develop new forms of collaboration that will advance research and education across the full spectrum of disciplines at Duke. The topics below show areas of research focus at Rhodes iiD. See all of our research.

Farm to Fork (Year 2)

A team of students collaborating with Duke School of Medicine's Root Causes Fresh Produce Program, community members, and physicians throughout the Duke Health network will help integrate data from food deliveries to Duke Health patients with patient health record data and other available data sources to create a dashboard that can analyze, predict, and manage the Root Causes' "Food as Medicine" program. Specific outcomes will contribute to improving the Program's quantitative evaluation of its health impact as well as efficiency and satisfaction for its patients. Students will be assisted with IRB approval and mentorship from faculty and community advisors.

Project Leads: Esko Brummel, Willis Wong

Melting Ice, Shifting Krill

A team of students led by researchers at the Duke Marine Lab will explore the changing distribution of krill around the Antarctic Peninsula. Krill are a key prey species in this ecosystem, supporting a number of animals including whales, seals, and penguins, but they are dependent on winter sea ice and may be in trouble as climate change progresses. Using data from acoustic zooplankton surveys, students will create maps and other products to visualize the spatial distribution of krill over the past 20 summers, then create metrics that allow us to quantify the way that krill distribution around the Antarctic Peninsula is changing as the climate shifts and ice melts. These results will be key to our understanding of the impacts of climate change on this polar ecosystem.

Project Lead: Douglas Nowacek

Project Manager: Amanda Lohmann

Data Science for Community Safety in Durham

A team of students will partner closely with the City of Durham's newly formed Community Safety Department. The Community Safety Department's mission is to identify, implement, and evaluate new approaches to enhance public safety that may not involve a law enforcement response or the criminal justice system. The student team will (1) analyze and identify geographic and temporal patterns in 911 calls for service, (2) conceptualize and build an abstracted data pipeline and tools that would enrich currently available 911 data with other social, economic, and health-related data, (3) explore associations between areas of high call volume, indicators of mental health distress, and histories of dispossession; and (4) identify methods by which future researchers could examine connections between varied 911 incident responses (e.g. police response, unarmed response, joint police, and mental health response) and life trajectories (e.g. arrest, jail time, hospitalization, unemployment, etc.).

Project Lead: Greg Herschlag, Anise Van, City of Durham

Learning to Communicate

Today we design communication networks using mathematical models that describe components of the system that affect end-to-end performance. As wireless links become more highly variable, and system components become harder to model, this approach is losing ground. A team of students led by Dr. Robert Calderbank, Dr. Christ Richmond, Dr. Lingjia Liu, Dr. Jeff Reed, and Carl Dietrich will develop machine learning (ML) algorithms that take advantage of special features of new waveforms proposed for 6G wireless communication. The team will be highly interdisciplinary, and will include students from Virginia Tech familiar with wireless communication, as well as students interested in machine learning. Students will design experiments, collect data, and analyze over the air performance, some working onsite using Virginia Tech’s CORNET testbed (https://cornet.wireless.vt.edu/), some virtually using CORENT-based remote lab experiments. The team will present their findings to clients at the Air Force Research Lab in Rome, NY.

Project Leads: Robert Calderbank, Christ Richmond, Lingjia Liu, Jeff Reed, and Carl Dietrich

Understanding electric consumption profiles with an emphasis on data privacy

This project is also part of Duke’s first Climate+ cohort

A team of students led by researchers at Duke and abroad will develop and evaluate machine learning solutions to model behavioral patterns of electric use, emphasizing data privacy. Data collected in different parts of the world will be analyzed to understand the electric patterns that characterize various appliances and how that information can model users' consumption profiles and prevent fraud.

Project Lead: J. Matias Di Martino

Plus Programs Data Exploration

Data+ has been in operation for 8 years, and several other linked programs have started up since, including Code+, which focuses on app development and CS+, which focuses on team-based research in Computer Science.
A team of students led by John Haws (OIT) will collaborate with Plus Programs administrators to review the data that has been gathered on students since each Plus Program began. The team will then make recommendations and create a single data structure and dashboard for Plus Programs that can be used for years to come to report on participants, suggest program improvements, and develop alumni outreach opportunities.

Project Lead: John Haws

Understanding the Course of Disease via Registration on Electronic Health Records Data

A team of students led by Professor Anru Zhang (Duke Biostatistics & Bioinformatics, Computer Science, Mathematics, and Statistical Science) will develop methods to investigate the courses of complex diseases through electronic health records. The team will apply tensor methods to identify key features to register the patient's timeline. This work will provide a basis for researchers at Duke and elsewhere to sufficiently utilize the high-dimensional and longitudinal information in the electronic health record data. If time permitted, the related methods and theory will also be studied.

Project Lead: Anru Zhang

Small Town Policing Accountability

The QSIDES Institute has pulled thousands of pages of police records from the Williamstown Police Department. This project will analyze and identify patterns in police behavior in the town, work with journalists and other activists to use the data to develop action plans to address problems and enact public safety reform, and help to build an abstracted process and suite of tools that can be used by other small towns and municipalities to analyze their own data and empower police reform efforts across the nation. This project will interface with the Small Town Policing Accounting, or SToPA Lab. The overall goal for this project is to use the instance of the Williamstown Policing data to build out a toolkit that can be used in other small municipalities for policing transparency.

Project Leads: Jude Higdon, Greg Herschlag

Exploring novel machine learning techniques for Brain Computer Interface (BCI) applications

A team of researchers associated with the Applied Machine Learning Lab in Duke’s ECE department will lead a team of students in developing novel machine learning techniques that will be used for improving brain computer interfaces (BCIs) using electroencephalography (EEG) data. Students will learn how to pre-process EEG data, extract EEG features, and train machine learning algorithms for character selection in a spelling interface that allows “locked in” individuals, like Stephen Hawking, to communicate with the outside world. In addition to developing machine learning algorithms, students will work to develop a dashboard to visualize EEG signals, trained classifier parameters, classifier outputs, and spelling decisions made by the BCI.

Project Lead: Leslie Collins

Pilot Earthquake Early Warning in Kathmandu

Data+ students led by Prof. Henri Gavin will develop AI models for on-site earthquake early warning, in which sensors at a site provide warnings at that site. The Data+ project will integrate into ongoing work on geophone sensors, IOT microcontrollers, and networking. The Data+ team will focus on machine learning aspects of the project by making use of extensive seismic databases. The machine learning model, an anisotropic Gaussian Process, will relate waveform characteristics from the initial moments of shaking to predict the maximum expected shaking at the monitored site.

Project Lead: Henri Gavin

Tracking climate change causes & impacts with satellites and AI

This project is also part of Duke’s first Climate+ cohort

A student team working with the Energy Data Analytics Lab will work to democratize access to data relevant to climate change mitigation and adaptation planning as well as the underlying models to acquire those data. This project will work towards building the first “foundation model” specifically for remote sensing imagery for the purpose of extracting climate change relevant content at scale to enable near real-time tracking of climate causes and impacts. A foundation model is a model (usually a deep neural network) that has been trained on a large and diverse set of data, after which it can be adapted to a variety of different (but related) inference tasks with a small fraction additional training data and computation. Leveraging recent developments in self-supervised learning, we will develop the dataset for creating this foundation model and begin training it on real-world data. A model developed using such a dataset will enhance climate change mitigation/adaptation monitoring and planning through developing robust features that can be used to monitor a broad range of climate change contributing factors (e.g. energy infrastructure and use, agricultural activity) and impacts (e.g. economic impacts and human migration) for informing climate mitigation and adaptation strategies.

Project Lead: Kyle Bradbury

Mapping the Trajectories of Duke Doctoral Students (Year 2)

A team of students led by Courtnea Rainey, David Jamieson-Drake, and Edward Balleisen will explore survey data from completers of the PhD and Duke PhD alumni to establish important correlations, document key patterns and longitudinal trends, and develop visualizations that can inform institutional decision-making. In addition to updating the work of last year’s Data+ team, this year’s group will use text mining and topic modeling to draw out key themes from the textual answers to free response questions. Combining statistics with data science and natural language processing to analyze large datasets, this team will help refine our efforts to improve doctoral training across Duke University.

Project Lead: Ed Balleisen

Improving infection detection efficiency with wearables

A team of students led by researchers in the BIG IDEAs Lab will work to create a cloud-based infection detection platform that populates and translates wearable data from a variety of sources. The project will involve working with existing wearable data pipelines (e.g., APIs) to collect, process, and visualize wearable device data in real-time as well as implement machine learning techniques to produce insights of user health. The project will also involve app development and UI/UX considerations so that the platform is easily accessible and user friendly. The ultimate goal of this work is to inform wearable device users of changes in their health condition before more serious symptoms occur.

Project Lead: Ali Roghanizad

Gamifying risk identification for alcohol use behaviors

A student team led by researchers at Duke Surgery and Global Health Institute will further develop the computer application - Alcohol Use Behavioral Phenotyping Test (AUBPT) that can help predict alcohol use and alcohol use disorder risks based on personal characteristics and behavioral performance on Research Domain Criteria paradigms/games. Students will build multi-tasking simulated AI agents using computational neuroscience and deep learning methods. These agents can 'mimic' human behaviors. Students will also use machine learning to model substance use risk from previously collected data. Together, these approaches will give a more rigorous understanding of causal relationships across behavioral paradigms and make AUBPT an adaptive application. This project is a part of the Bass Connections project - 'Alcohol Use Behaviors across Countries and Cultures' (https://bassconnections.duke.edu/project-teams/alcohol-use-behaviors-across-countries-and-cultures-2021-2022). The Bass Connections team is highly interdisciplinary where students are working at the interface of digital, mental, and global health to deployment, evaluation, and cultural adaptation of our AUBPT across multiple global samples. The Bass Connections team is highly interdisciplinary where students are working at the interface of digital, mental, and global health for deployment, evaluation, and cultural adaptation of AUBPT across multiple global populations.

Project Lead: Siddesh Zadey, Dr. Catherine Staton and Dr. Joao Vissoci

Investigating wetland carbon emissions in the SE US under climate change

This project is also part of Duke’s first Climate+ cohort

A team of students led by researchers in the Hydroclimatological Lab will comprehensively quantify the wetland carbon emissions in the entire Southeast (SE) US using machine learning techniques and various climate datasets—including in situ measurements, remote sensing data, climate observations, and hydrological model (PIHM-Wetland) outputs. Students will first apply machine learning techniques to establish the relationship between hydroclimatological variables and wetland carbon emissions at observational sites. Spatial distributed carbon emissions from the entire SE US wetland ecosystems will be created afterwards. Based on the current climate analysis, future wetland carbon emissions will be predicted in a warming climate. This research will better assess wetland carbon emissions over the entire Southeast and provide critical information on future carbon budgets on regional scales.

Project Lead: Wenhong Li

Finding Medieval Irish People Using Drones: The HELM Project

A team of students led by Co-Principal Investigators Dr Jenny Immich and Dr Vicky McAlister will develop a geospatial methodology to automate data analysis originating from small unmanned aerial vehicles (SUAV) that seeks to identify the homes of ordinary medieval people within the modern Irish landscape. Known as aerial archaeology, this work investigates archaeological remnants on the surface of the earth without excavation. Students will create iterative Python scripts to analyze elevation datasets (hillshades) in areas surrounding medieval castles. Students will create advanced analysis methodologies for exploring low-lying archaeological features in the landscape, including principal component, standard deviation, and difference mean elevations. Students with interest and appropriate backgrounds will be challenged to develop machine learning methods for identification of linear archaeology. The resulting portfolio of work will be robust, including workflows, metadata, methodologies, and scripts. This work will solidify geospatial methodologies in advancing our knowledge of where everyday people lived in Ireland during the medieval period, a question that has long perplexed archaeologists. In addition, it will fundamentally ground our understanding of complex topics in urbanization to the modern period and shed light on the development of communities across time.

Project Lead: Vicky McAlister, Southeast Missouri State University

Modeling microbial growth to understand pathogenesis and biological resilience and resilience

The goal of this Data+ project is to apply and extend custom analytics solutions to understand and predict microbial population growth. An explosion of data has resulted from tracking the growth of bacteria in high throughput devices. These data were generated to understand how microbes grow. Better models that fit and predict these growth data are needed for better treatment of pathogenic bacterial infections, food safety, beer and bread fermentation, and understanding stress resilience of the microbiome. Using nonparametric statistical models to analyze how microbes grow under stress, the Schmid research lab at Duke has made important discoveries in these areas. These studies generated large data sets and developed statistical models to track and predict how microbes grow and change their gene expression when faced with extreme stress. We built a web application called phenom to make these models accessible to the broader community. In this Data+ project, students will beta test the web app and make improvements, including data visualization, extending the underlying statistical model, and analyzing data using the app.

Project Lead: Amy Schmid

Image credit: Tonner, P.D., Darnell, C.L., Bushell, F.M.L., Lund, P.A., Schmid, A.K.*, Schmidler, S.C. 2020. A Bayesian non-parametric mixed-Effects model of microbial growth curves. PLoS Comp Biol. 16(10): e1008366. https://doi.org/10.1371/journal.pcbi.1008366

Predictable Control of Spatial Patterns Formed by Bacterial Consortia

A team of students led by Biomedical Engineering professor Lingchong You will predict pattern formation of bacterial colonies by integrating experimental results with both mechanistic modelling and machine learning methods. Bacterial colonies have the capability to self-organize into beautiful and intricate patterns. Students will contribute to a method for controlling the outcome of colony spatial patterning, which is an important challenge facing the field of synthetic biology.

Project Lead: Lingchong You

River ice timing and duration in a warming climate: Field camera image classification

This project is also part of Duke’s first Climate+ cohort

Duke Data+ students, in collaboration with Dr. Emily Bernhardt (faculty advisor) and Audrey Thellman (graduate student) will evaluate how changing ice and snow conditions are impacting river ecosystems through classified ice imagery. Currently, our team has data from 7 field cameras that have been taking photos of the stream channel each day since 2018. We have created training data and code for a machine learning classifier to transform these photos into ecologically relevant indices, such as percent snow coverage. The Data+ team will modularize and visualize this classification pipeline to increase accessibility of our data product. Students will have the opportunity to work with a team of scientists at the New Hampshire site, U.S. Geological Survey partners with vested interest in the data product, and data scientists working in the Bernhardt Lab who have completed and are currently working on similar projects that increase availability and usability of environmental data (see https://cuahsi.shinyapps.io/macrosheds/).

Project Lead: Audrey Thellman, Emily Bernhardt

Policy surveillance of UHC financing in Developing Countries

A team of students led by researchers at the Duke Center for Policy Impact in Global Health (CPIGH) will create a user-friendly interactive visualization tool to track the evolution of Universal Health Coverage (UHC) financing policies in the low- and middle-income countries. The students will use the UHC policy surveillance data collected by the CPIGH Bass Connections team in the Fall 2021 and Spring 2022 semesters. This publicly available data visualization will provide an opportunity for policymakers and researchers to conduct a quick comparative cross-country analysis and longitudinal analysis to understand the impact of different policy experiments on UHC progress in different jurisdictions.

Data+Fest: Building a dashboard and educational resources for DataFest

A team of students led by Statistical Science professors Mine Çetinkaya-Rundel and Maria Tackett will pull together all data associated with DataFest (https://www2.stat.duke.edu/datafest) for the purpose of retrospective archiving and documentation as well as creating a valuable resource that can serve as the one-stop-shop for students interested in participating in DataFest in the future. Goals of this project include curating “metadata” on past DataFests to build an interactive dashboard that shows the growth of the event (over time and over geographies) as well as highlights winning projects and participants, creating educational materials based on data from past DataFests that students can use to prepare for the event, and building a website that will serve as the student landing page for the global DataFest event and showcase all products of the Data+ projects. Students will develop their skills working with R packages like Shiny (to build the dashboard), blogdown (to build the website), and a large number packages for data wrangling, visualization, and modeling. All content developed as part of this project will be available to DataFest sites and over 3000 annual participants.

Project Leads: Mine Çetinkaya-Rundel and Maria Tackett

A city and its river: Contaminant Risk in Durham

A team of students led by researchers in the Duke River Center will develop a publicly available and accessible website to serve as a portal to explore diverse and extensive datasets detailing the quality of waterways and the effectiveness of management efforts to reduce risks associated with chemical contaminants, stormwater flow, and flooding. For example, these datasets are critical in developing mitigation efforts to prepare for changing and new climatic patterns (e.g., extreme weather events and flooding, drought and protecting drinking water resources). However, the data is not readily accessible and easy to visualize for the general public. The website will be developed in collaboration with our community collaborator, the Ellerbe Creek Watershed Association, and Data+ teammates will have the unique opportunity to engage with a separate NSF-funded workshop focused on teaching tools for visualizing these datasets; the workshop will bring together ~30 early scientists across academia, government, and industry.

Project Leads: Emily Bernhardt and Jonathan Behrens

AI-powered Transcription of Historical Manuscripts

A team of students will collaborate with Duke librarians to use AI-powered Handwriting Text Recognition (HTR) tools to transform thousands of pages of handwritten text into machine readable data. Using a large dataset of digitized 19th and early 20th-century women’s travel diaries held in the Rubenstein Library students will test and evaluate various HTR technologies, document methods and constraints for extracting text from historical manuscripts, and build an HTR toolset and proof-of-concept interface that the library can build on for future projects. This work will further the library’s initiative to make its historical collections more readily available for computational research (and future Data+ projects!).

Project Leads: Molly Bragg and Noah Huffman

Mental Health and the Justice System in Durham County

A team of students led by researchers Nicole Schramm-Sapyta (Duke Institute for Brain Sciences) and Maria Tackett (Statistical Science) will explore the impacts of community health services and local laws and policies on the justice-involved population in Durham. The team will create a public-facing interactive timeline of the implementation of mental health services, drug laws, and court policies in Durham; the data used to create the timeline will also be incorporated into the team’s ongoing analyses. Students will also analyze data from the Durham County Detention Center and Duke Health to explore the impact of the COVID-19 pandemic on incarceration and health-care utilization for the justice-involved population, along with the effects of policies related to mental illness and justice involvement. The data sets and analysis produced in Data+ will provide a foundation for the team’s research in Bass Connections during the 2022 - 2023 academic year. Students are asked to commit to working with the team for Summer, 2022 (Data +) as well as Fall and Spring 2022-2023 (Bass Connections).

Project Leads: Nicole Schramm-Sapyta and Maria Tackett

Analyzing the Gap in Cancer Control Equity in China

A team of students led by faculty from both Duke and Duke Kunshan will synthesize data from a variety of sources to investigate the social determinants of cancers in local areas, examine the impact of personal behaviors (such as diet, sleeping, exercise, smoking) and community characteristics (such as air/water/soil quality, built environment, social norms, discrimination, marginalization) on cancer-related outcomes, and conduct systematic review and meta-analysis to evaluate the effectiveness of the current cancer prevention and control policies and interventions in China. The findings will provide rich empirical evidence to describe the cancer burden/disparity and its causes, identify the state-of-the-art cancer prevention and control practices, and inspire the development of region-specific and population-tailored policies and interventions to close the equity gap in cancer prevention and control in China.

Project Lead: Meifeng Chen

Visualizing Durham Public School Communities

Using data from the Durham Compass and the NC School Report Card among many other sources, this team will continue the development of an interactive R Shiny dashboard that permits exploration of school statistical data. The team aims to explore school zones through an asset-based lens in an effort to support ethical and imaginative partnerships between Duke, North Carolina Central, and Durham Public Schools. This is a continuation of a joint Duke-NCCU Bass Connections project.

Project Lead: Alec Greenwald

Ethical Consumption before Capitalism Year 3

Is there a right type and amount of consumption? The idea of ethical consumption has gained prominence in recent discourse, both in terms of what we purchase (from fair trade coffee to carbon off-sets) and how much we consume (from rechargeable batteries to energy efficient homes). These modes of ethical consumerism assume that individuals become political, as well as economic, actors through shopping. Concern with the morality of consumption is not new to capitalist societies, and we can see as much in the earliest discourses surrounding the market economy. During the Middle Ages and the Renaissance, acts of consumption became increasingly aligned with corruption, as individual and corporate bodies were depicted as altered, even damaged, by trade. And, in an increasingly global and colonial economy, authors debated the ethics of expanding into new markets from India to the Americas. These questions and others like them have shaped our own modern discourse around the ethics of consumption.

Building on the past two years of work, this project will extend the analysis of consumption performed in 2020 and 2021 to include the data collected and analyzed by the Bass Connections team from the rare materials archives of Duke’s Rubenstein library and of the University of Alabama Birmingham’s Lister Hill library. These materials include Medieval and Early Modern medical manuals, which will help us to analyze the metaphorical translation from medical consumption of the human body to economic consumption of the body politic; seventeenth-century mercantile theory texts, which theorize how consumption is connected to trade and monetary policy; as well as treatises and legislative documents on monopolies, corporations, and trading companies.

Project Leads: Astrid Giugni, Jessica Hines

AdoptADrain: working with citizen science data to understand plastic pollution within stormwater

A team of students led by Dr. Liz DeMattia (Duke University Marine Lab) and Dr. Rachel Noble (UNC-IMS) will explore the Community Science Initiative’s AdoptADrain citizen science data collected during the 2021/2022 academic year (the first year of the program). Potential data analyses will include: collating, organizing, comparing and contrasting, finding trends, and comparing the AdoptADrain data to other marine debris data from NC. In addition to analyses, students will also explore best practices for displaying information, communicate findings to the general public, and potentially develop new programs to help with data collection. This work will provide the needed mobilization of raw citizen science data into useable information for participants, the public and policy makers.

Project Lead: Dr. Liz DeMattia

American Predatory Lending (Year 3)

Alexa Goble (Finance) joined Econ majors Chavez Cheong and Eli Levine in a ten-week exploration of mortgage enforcement actions related to the financial crisis from earlier in this century. Using NLP techniques on mortgage data from Ohio and Massachusetts, the team validated a new experimental approach to understanding the dynamics between state regulatory agencies, mortgage lenders, brokers, and loan originators. This project was a continuation of two previous Data+ projects:

https://bigdata.duke.edu/projects/american-predatory-lending-global-financial-crisis

https://bigdata.duke.edu/projects/american-predatory-lending-and-global-financial-crisis-year-2

View the team's project poster here

Watch the team's final presentation on Zoom:

Project Lead: Lee Reiners

Project Manager: Malcolm Smith Fraser

Redistricting School Zones in Durham County

Stats/Sociology major Mitchelle Mojekwu joined Neuroscience majors Kassie Hamilton and Zineb Jaidi in a ten-week exploration of data relevant to an upcoming public school zone redistricting in Durham County. Using information acquired from the General Social Survey and the US Census, the team applied modern mathematical and statistical methods for generating proposed redistricting plans, with the aim of providing decision-makers with information they can use to produce school districts that are equitable and reflective of the Durham County student population.

View the team's project poster here

Watch the team's final presentation on Zoom:

Faculty Lead: Greg Herschlag

Project Manager: Bernard Coles

Agile Waveform Design in the Presence of Opposition: Quantifying Performance

Pryia Juarez (BME/ECE), Jonathan Pilland (ECE/BME), and Matthew Traum (CS/Econ) spent teen weeks analyzing sensor data synthesized by an agile waveform generator. The team used deep reinforcement learning techniques to understand the performance of different synthetic agents representing potential attackers to the sensor system.

View the team's project poster here

Watch the team's final presentation on Zoom:

Faculty leads: Robert Calderbank, Vahid Tarokh, Ali Pezeshki

Client leads: Dr. Lauren Huie, Dr. Elizabeth Bentley, Dr. Zola Donovan, Dr. Ashley Prater-Bennette, Dr. Erin Trip

Project Manger: Suya Wu

Dashboard for Public Investments

Xixi Lei (CS), Raffey Rana (CS/Econ), and Fan Zhu (Stats) spent ten weeks building tools to enable DUMAC to track and visualize its investments and their performance. The team cleaned data, met with stakeholders, and delivered an interactive dashboard in Tableau.

View the team's project poster here

Watch the team's final presentation on Zoom:

Project Lead: Yi Wang

Project Manager: Christopher Ritter

Benefiting from NLP Tools in the Investment Office

Keith Cressman (CS/ECE), Isa Lu (Econ), and Ivan-Aleksandr Mavrov (Econ/Math) spent ten weeks exploring how NLP tools could be put to use to improve document analysis workflow at DUMAC Inc., which is responsible for managing the assets of Duke University.

View the team's project poster here

Watch the team's final project presentation on Zoom:

Detecting and Matching Similar Networks

Louis Hu (CS/Math), Fayfay Ning (Math/CS), and Kieran Lele (CS/Sociology) spent ten weeks exploring methods for exploring the similarities between networks of massive size, such as those arising from social media or from protein-protein alignment. The team used a variety of mathematical and software techniques and delivered a comprehensive analysis to experts in the field.

View the team's project poster here

Watch the team's final presentation on Zoom:

Project Lead: Jianming Xu

Project Manager: Sophie Yu

Data Visualization for Family Health

Shannon Houser (Stats/BioChem), Junbo Guan (MIDS), and Gaurav Sirdeshmukh (Stats) spent ten weeks exploring data concerning child and family health in Yolo County, CA. Using R Shiny, the team produced an interactive data dashboard that enables Yolo County residents to find healthcare and childcare providers, food resources, and transportation information.

View the team's project poster here

Watch the team's final presentation on Zoom:

Project Lead: Leigh Ann Simmons (UC Davis)

Creating artificial worlds with AI to improve energy access data

Caroline Tang (Math/Stats) joined CS majors Frankie Willard and Alex Kumar in a ten-week exploration of AI methods to improve the mapping of energy infrastructure within satellite imagery. The team used cutting-edge methods to create synthetic imagery that, when blended with real imagery, improved the performance of deep learning methods on the energy infrastructure detection task.

View the team's project poster here

Watch the team's final presentation on Zoom here:

Project Lead: Kyle Bradbury

Project Manager: Wei Hu

Understanding Voting Patterns and Interactions with Gerrymandering

Martin Guo (MIDS), Dani Trejo (CS), James Wang (CS/Math), and Grayson York (Math/CS) spent ten weeks building tools to understand voting patterns and gerrymandering of districts in North Carolina. They used dimension reduction techniques to cluster different elections into common groups, and they tested various methods for generating synthetic elections for comparison.

View the team's project poster here

Watch the team's final project presentation on Zoom:

This project is part of an ongoing set of projects by the sponsoring faculty around Voting, Gerrymandering and Democracy. See their blog ( https://sites.duke.edu/quantifyinggerrymandering/) for more information and projects from previous years of Data+ and Bass Connections.

Project Leads: Greg Herschlag, Jonathan Mattingly

Predicting Baseball Players’ Athletic Performance

Simi Bleznak (Math/AI), Max Brown (Math/Econ), and Julia Choi (Bio) spent ten weeks Exploring how visual, cognitive, and physical abilities relate to physical performance can provide insight into the development of athletes. Using two rich datasets provided by USA Baseball, the team used linear regression, logistic regression models, and longitudinal methods to deliver key insights to decision-makers. This project was a continuation of a Data+ project from last summer: https://bigdata.duke.edu/projects/predicting-baseball-players%E2%80%99-athletic-performance

View the team's project poster here

Watch the team's final presentation on Zoom:

Project Leads: Marc Richard, Suhail Mithani, Greg Appelbaum

Project Mangers: Billy Carson and Hunter Klein

CovIdentify

Sean Fiscus (Math/Econ/EnvEng), Alyssa Shi (Stats), Yamil Lopez-Ruiz (BME/CS), Emmanuel Mokel (Stats/Math) spent ten weeks working with data from CovIdentify, a study that focuses on using wearables to predict and diagnose COVID-19 and the Flu. The team improved the memory efficiency of analytic pipelines, and added capacity to ingest different types of data. This project built upon the work accomplished by the Duke Bass Connections team and the Duke MIDS capstone project.

View the team's project poster here

Watch the team's final presentation on Zoom:

Project Lead: Jessilyn Dunn

From Farm to Table

CS majors Aiman Haider and Divya Nataraj spent ten weeks analysing data and developing tools to assist the Fresh Produce Program (FPP) in achieving its core goals of creating a more equitable, sustainable, and integrated local food system. Using modern geospatial data analysis techniques, the team identified optimal locations for food distribution hubs, analyzed demographic data about the distribution area, and built an ArcGIS web app to allow interactive exploration of their results.

View the team's project poster here

Watch the team's final presentation on Zoom:

Project Lead: Willis Wong

Pivers Island Coastal Observatory

Stats majors Alexandra Lawrence and Morgan Pruchniewski spent ten weeks exploring a dataset comprising 619 variables, including chemical and biological measurements, sourced from the Pivers Island Coastal Observatory (PICO). Using modern time-series analysis techniques, the team delivered key insights to PICO scientific staff, as well as advice for future data collection protocols.

View the team's project poster here

Watch the team's final presentation on Zoom:

Project Lead: Zackary Johnson

Web Attack Features

Jayesh Gupta (ECE/CS), Trevon Helm (ECE), and Yvonne Kuo (CS/PoliSci) spent ten weeks developing tools to extract features from network data in collaboration with information security professionals with Duke’s OIT. The team performed exploratory data analysis to extract features and used machine-learning techniques to detect zero-day attacks. This project was sponsored by Cisco, Inc.

View the team's project poster here

Watch the team's final presentation on Zoom:

Project Lead: Eric Hope

Project Manager: Pranav Manjunath

Visualizing Durham Public School Communities

Patience Jones (NCCU, Psychology and Elementary Education) joined Duke students Allyson Ashekun (PubPol), Drew Greene (PubPol), and Rhea Tejwani (CS/Econ) in a ten-week curation of data meant to assist decision-makers within Durham Public Schools. Using data from the Durham Compass and the NC School Report Card among many other sources, the team produced an interactive R Shiny dashboard that permits exploration of school statistical and geospatial data. This was a continuation of a joint Duke-NCCU Bass Connections project (https://bassconnections.duke.edu/about/news/how-duke-and-nc-central-university-are-inthistogether-support-durham-schools).

View the team's poster here

Watch the team's final presentation on Zoom:

Project Lead: Alec Greenwald

Project Manager: Nicolas Restrepo Ochoa

Modeling microbial growth and resilience

Molly Borowiak (CS) and Joshua Tennyson (CS/BME) spent ten weeks building tools to assist in the analysis of data arising from microbial growth experiments. The team produced a comprehensive Python package that enables the exploration of a variety of modeling techniques with the data.

View the team's project poster here

Watch the team's final project presentation on Zoom:

(photo credit: Peter Tonner et al., 2020 PLoS Computational Biology https://journals.plos.org/ploscompbiol/article/comments?id=10.1371/journal.pcbi.1008366 )

Project Lead: Amy Schmid

Project Manager: David Buch

The Impact of Virtualized Museum Collections

Annie Xu (Rice, CEE), Liuren Yin (ECE), and Zoe Zhu (Data Science) spent ten weeks analysing usage data for MorphoSource, a publicly available 3D data repository maintained by Duke University. Working with Python and Tableau, the team developed an interactive dashboard that allows MorphoSource staff to explore usage patterns for site visitors who view 3D files representing objects from primate skulls to historical art pieces.

View the team's project poster here

Watch the team's final presentation on Zoom here:

Project Leads: Doug Boyer, Julia Winchester

Constructing Utopias in Restoration London

After London was destroyed during the Great Fire of 1666, it was reconstructed into the “emerald gem of Europe,” a utopian epicenter focused on England’s political and economic interests. For whom was the utopia constructed? Who determined its architectural choices? And what did such a utopia look like in seventeenth-century London?

Our research uses Natural Language Processing to analyze semantic trends in digitized text from the online database “Early English Books Online” (EEBO-TCP https://textcreationpartnership.org/tcp-texts/eebo-tcp-early-english-books-online/) to answer such questions. After applying methods such as word-embedding, sentiment analysis, and hapax richness, we provide an overview of themes in the seventeenth century; specifically, we conducted case studies on changes to coal taxes within the period and the reconstruction of St Paul's Cathedral. Our results thus show that, while a utopian society was originally intended to be built for the people, the project’s motivation eventually shifted to a political purpose, as evidenced by the approval of more costly city projects. In response to backlash against the increase of taxes on coal to support large-scale building projects, the ruling class highlighted positive outcomes in printed materials in order to convince working class persons that their collected taxes contributed to a greater good, despite evidence to the contrary. Finally, during key historical events, sentiment and hapax richness are shown to have an inverse relationship, the results of which can demonstrate how London writers engaged with text and genre as forms of protest.

View the team's project poster here

Watch the team's final project presentation on Zoom:

Mapping the Trajectories of Duke Doctoral Students

Evan Dragich (Stats/Bio) and Katie Tan (Econ) spent ten weeks working with two sets of survey data provided by alumni of the Duke Graduate School. After cleaning data, the team used R Shiny to build an interactive dashboard that can assist leadership aiming to improve the direction and quality of Duke doctoral education.

View the team's project poster here

Watch the team's final project presentation on Zoom:

Project Lead: Ed Ballesein

Project Manager: Sarah Nolan

Mental Health and the Justice System in Durham County (Year 4)

Brianna Cellini (Global Health, Neuroscience), Kexin (William) Feng (Public Policy, Philosophy), John Liakos (Neuroscience), and Maya Pandey (Political Science, Public Policy) received updated data from the Durham county sheriff’s office and Duke health, adding data from 2019-2020. They spent the summer cleaning that data, comparing past demographics and descriptive statistics to the new data, and preparing to analyze the effect of COVID and new Durham County policies on incarceration and health service utilization. They also established a new criterion to indicate which patients experience severe mental illness, based on health system records, to complement the mental health tagging system from the detention facility.

View the team's project poster here

View the team's final presentation on Zoom:

Project Lead: Nicole Schramm-Sapyta

Project Manager: Ruth Wygle

Rainforest XPRIZE

Tejvasi Patil (MEM), Sophia Stameson (CS), and Larry Zheng (Bio) spent ten weeks working with drone footage from different rainforest sources. The team designed a pipeline that performed image classification on the drone footage, and curated a training dataset using SQL.

View the team's project poster here

Watch the team's final presentation on Zoom:

Project Lead: Martin Brooke

Project Manager: Ryan Huang

Ethical Consumption Before Capitalism

Is there a right type and amount of consumption?

Rubenstein Library’s Card Catalog File

Heidi Smith (CS, English) and Biniam Garomsa (DataScience, Math) spent ten weeks building tools to assist the David M. Rubenstein Rare Book and Manuscript Library’s mission of finding and describing historically marginalized voices within their collections. The team performed extensive data wrangling, including modern optical character recognition techniques, with the card catalog, and then did a demographic analysis and a topic modeling analysis with the results. Final deliverables to library professionals included a structured dataset, an interactive web app, and a search tool.

View the team's project poster here

Watch the team's final presentation on Zoom:

Project Leads: Meghan Lyon

Project Manager: Anna Holleman

Predictive Maintenance of F15s

The Air Force’s F-15E Strike Eagle jets have parts that wear down and break, causing unscheduled maintenance events that take away valuable time in the air for critical missions and training. Our team, Limitless Data, is working with Seymour Johnson Air Force Base to mine manually entered maintenance data to visualize and predict aircraft failures. We created a prototype data visualization product that will enable maintainers on the flight line and help them identify and repair critical failures before they happen, keeping jets ready to fly, fight and win.

Neural Network-Based Self-Adjusting Computational Processors

This project aims to improve the computational efficiency of signal operations, e.g., sampling and multiplying signals. We design machine learning-based signal processing modules that use an adaptive sampling strategy and interpolation to generate a good approximation of the exact output. While ensuring a low error level, improvements in computational efficiency can be expected for digital signal processing systems using the implemented self-adjusting modules.

Computational Approaches to the History of Cartography

Mapping History has focused on the categorizing, labelling, digitization, and 3D reconstruction of 16^th & 17^th century maps & atlases of London and Lisbon. Over the course of the summer, the Mapping History team has developed its own unique analytical dataset by painstakingly labelling every element contained within these maps, used python to digitize this dataset, and, now in the projects final stage, has begun the process of reconstructing these historical perspectives in a 3D game engine.

Data Science for Retention of College Women in Tech

For our Data+ project, we partnered with Rewriting the Code (RTC), a non-profit organization committed to empowering and fostering a community of college women with a passion for technology. We developed company and industry profiles for the recruitment process that included information ranging from interview and offer rate to negotiation success of salary and benefits. Additionally, we conducted text-analysis of resumes to understand the structure of an optimal tech resume and utilized linear regression to determine the influence of different variables such as ethnicity or college rank.

AI in the Investment Office

Our team used artificial intelligence to help Duke University Management Company (DUMAC) operate more efficiently by building a cost optimization tool and analyzing and visualizing venture capital data. In our first project centered around cost optimization, we designed a Python script that suggests optimal cash transfers between prime brokers. In our second project, we utilized web scraping and Tableau to aid DUMAC in understanding the relationship between company age and length of current investments.

Applying Security Orchestration, Automation & Response (SOAR) to security threat hunting with Duke’s ITSO

We utilize elements of data science and analysis in order to scour weblogs for potential malicious attacks on Duke’s servers. Additionally, we seek to identify patterns within the data that could be indicative of malicious intent and hope to apply these to real-time data.

Predictive Churn Models for Duke Season Ticket Holders and Annual Donors

Predictive Churn Models for Duke Season Ticket Holders and Annual Donors is centered around understanding which annual donors are most likely to churn, i.e. not donate the following year. To solve this problem the team built different models to predict the profiles and timing of donor churn. The team made use of Duke Athletics’ internal data supplemented by external data to build predictive machine learning models.

Piloting an Environmental Public Health Tracking Tool for North Carolina

Our team members have spent the summer working with the North Carolina Division of Public Health Occupational and Environmental Epidemiology Branch to build a pilot environmental public health data dashboard, with the hope that the pilot tool will be used in DPH’s grant proposal to the CDC for a fully-funded tool. The pilot tool, which is a Tableau dashboard, displays population, health, and environmental data for North Carolina counties and census tracts. The project involved data processing in R, the creation of a detailed metadata table, and building interactive visualizations Tableau.

American Predatory Lending and the Global Financial Crisis (Year 2)

Carrying forward the work of a 2019-20 Bass Connections team, our Data+ team has worked to better understand the state of the home mortgage market leading up to the financial crisis. The team has built a more in-depth analysis of North Carolina to understand its different regions. We have also expanded the scope of the analysis developing a quantitative portrait on the state of the mortgage market in Arizona, Florida, Massachusetts, Georgia, and Ohio, creating visualization devices for different mortgage market statistics.

Linking Urban Land Use to Aquatic Metabolism Regimes

Our group aims to reveal the effects of urban and agricultural land use on metabolic productivities of rivers through statistical manipulation and visualization. During this summer, we classified sites and conducted covariate analyses based on patterns of metabolism, and produced reproducible code that can be used by researchers with similar research goals. We hope that our findings would suggest hypotheses of how disruption is caused by land development, and what factors should land planners avoid introducing.

Predictive Modeling of Mechanical Failures at Sea

Our team used years of unanalyzed data in a cloud computing environment to conduct exploratory data analysis using natural language processing techniques, as well as visualizations, for Fleet Management Limited. Through this, and preliminary predictive modelling, we hope to help management decrease the number of preventable incidents as each one costs FML more than $10,000.

Deep Learning for Rare Energy Infrastructures in Satellite Imagery

We trained an object detection model to locate wind turbines in overhead satellite imagery. Because these deep learning models require large amounts of training data, and satellite imagery of wind turbines is rare and expensive to collect, we created synthetic satellite imagery using 3D modeling software. We then supplemented our real-world training dataset with the synthetic imagery and observed changes in performance.

Finding Space Junk with the World’s Biggest Telescopes

Astronomers from the Dark Energy Survey rely on images of deep space to understand the nature of the universe, but these images are often polluted with "space junk": asteroids, comets, satellites, or other objects from our own solar system obstructing the telescope's view. In order to perform their analysis, scientists must first manually identify and mask out such objects from images, a time-consuming process. With leads Michael Troxel, Dan Scolnic, and Chris Walter, we've leveraged deep learning-based computer vision techniques to build models to automatically identify and localize space junk in deep space imagery.

Project Lead: Dan Scolnic, Michael Troxel, Chris Walter

Click here to view the team's final project

Forecasting campus energy usage for improved energy management

In collaboration with Data and Analytics Practice at OIT, our team has completed a series of critical analyses aiding Duke Facilities Management in further optimizing campus energy usage. Data cleaning tools, imputation techniques, and a variety of time series prediction methods ranging from autoregressive models to deep learning networks have been seamlessly integrated into a single interactive forecasting application allowing collaborators to provide accurate and comprehensive utility usage estimates.

Race and Housing in Durham over the Course of the 20th Century

Our team examined the relationship between race and home values across several units of analysis (household, address, HOLC rating area, census block, block group, and tract) in Durham, NC. We combined data from the decennial censuses (1940-2010), American Community Survey (2005-2018), Durham County Register of Deeds (1997-2020), and Durham County Tax Administration (1997-2021). We find that home values are strongly associated with the racial composition of areas, that homes in black neighborhoods are worth less, and that they accumulate less value over time.

Predicting Blindness in Duke’s Glaucoma Patient Population

This project involves predicting the incidence of blindness in glaucoma patients at Duke Eye Center (DEC) -- specifically, the likelihood of a patient presenting legally blind (i.e. with very advanced disease) at their first visit. We will assemble a novel data set of electronic health records from thousands of DEC glaucoma patients and data from the Durham Neighborhood Compass project, a repository of geospatially resolved socioeconomic statistics on Durham county that includes features like average distance to a healthcare facility. We aim to identify risk factors associated with delayed care for glaucoma in the Durham and wider NC communities.

Network Visualization of Foot Traffic Patterns

In light of Duke’s reopening amidst the COVID-19 pandemic, this project aims to track the movement of foot traffic in and around Bryan Center by analyzing Wifi log data from all users connected to wireless networks in the center during February 2020. Our team employed Markov Chains, Kernel Density Estimations, and data analysis and visualization tools such as Python and Tableau to create a map of Wifi access points in Bryan Center and a heatmap that visualizes congestion in different floor areas across time. Our goal is to provide Duke OIT and Student Affairs with valuable information on highly congested areas and frequented paths, directing social distancing measures and suggesting alternative paths that can reduce transmission-risk this coming academic year.

Project Leads: John Haws, Mary Thompson, Eric Hope, Sean Dilda

Project Manager: Hunter Klein

Click here to view the project team's poster

Watch the team's final project presentation (on Zoom) here:

Mental Health and the Justice System in Durham County

This summer, our objective was to take data provided by the Durham County Detention Facility (DCDF), Duke Health, and Lincoln Community Health Center and analyze trends across the local justice system and these health care institutions, specifically in regards to individuals with mental illness. We analyzed the experience of individuals who were incarcerated by looking at their demographic characteristics, emergency department usage, and criminal justice encounters. Using these initial findings, we hope to better understand the relationship between health care utilization and rates of recidivism in Durham County during the school year through a Bass Connections Team.

Project Leads: Nicole Schramm-Sapyta, Maria Tackett

Project Manager: Ruth Wygle

Click here to view the team's final project summary

Watch the team's final presentation (on Zoom) here:

Latinxs and the Right

The visibility of hate groups such as the Alt-Right became mainstream into contemporary political culture during the Unite the Right Rally in Charlottesville, VA in 2017. This project aims to explore methods to quantify the presence of Latinxs within the Alt-Right, particularly in how they racialize themselves in a space that often spews hate towards Mexicans and other marginalized groups from Latin America. Using data from multiple sources (such as Twitter, Stormfront, and Breitbart), we developed a corpus of tweets, subthreads, and articles, and analyzed this data using basic natural language processing (NLP) techniques.

Predicting Baseball Players’ Athletic Performance Utilizing Baseline Assessments of Vision

This project aims to analyze assessment and performance data collected from baseball players to make predictions about baseball performance based on vision and physical abilities. We use hierarchical regression analyses to identify characteristics that correlate with batting performance in order to inform scouts about the likely production of developmental prospects. The final product is an application that uses an athlete's assessment results to produce performance summary graphs for the individual compared to other athletes and inferential models for the relationships between assessments and performance.

Project Leads: Greg Appelbaum, Marc Richard, Joel Huber

Click here to view the team's project poster

Watch the team's final presentation (on Zoom) here:

For love of greed: tracing the early history of consumer culture

We apply word embedding models to corpora from the start of the Early Modern period, when the market economy began to dramatically expand in England. Word embedding models use neural networks to map vectors to words so that semantic relationships are preserved within the vectors’ geometry. Such models have been successful in understanding cultural trends and stereotypes in large corpora of texts, but these techniques are infrequently used on texts dating much farther back than the 19th century. Using newly developed methods for analyzing word embeddings, we track the development of the meanings of words related to consumerism, including their relationships with gender over time.

Protecting American Investors? Financial Advice from before the New Deal to the Birth of the Internet

The Protecting American Investors project investigates the evolving structure and content of financial advice from the early 20th century to the birth of the Internet. By converting and cleaning thousands of investment advice columns from historical newspapers and magazines, we assembled a large corpus to address our research questions. Through text analysis methods like topic modeling, we have seen how the business cycle affects the nature of advice, the speed in which different financial innovations were integrated, and how advice differs among various targeted social groups.

Project Lead: Ed Balleisen

Click here to view the team's final project summary slides

Watch the team's final presentation (on Zoom) here:

On Being a Blue Devil: the changing profile of the Duke student body

Duke’s enrollment data over the past 50 years speaks volumes about the evolution of the University. Using physical scans courtesy of the Duke University Archives, we manipulate decades of demographic and geospatial data across all Duke schools to create an interactive application. Giving users control over how they want to dive into the data, we hope to both illuminate questions and inspire further research into the composition of Duke’s student body--highlighting the history, origins, and people that have helped make it what it is today.

Project Leads: Don Taylor, Valerie Gillispie

Project Manager: Anna Holleman

Watch the project team's final presentation (on Zoom) here:

The team discusses insights they have learned through looking at Duke's enrollment data since the founding of Duke:

Taking electrification on the road: Exploring the impact of the Electric Farm Equipment roadshow

Between 1935 and 1945, rural electricity access shot up from roughly 10% to 90%. During this time, the Rural Electrification Administration funded an Electric Farm Equipment (EFE) Roadshow as part of its mission to expand electricity access and demand. Digitizing massive amounts of archival data, our team has sought to quantify the effect of the EFE Roadshow on the larger trend of growing residential electricity consumption in rural U.S. towns from 1938 to 1945. We hope that understanding this crucial chapter in our own history will help inform present-day electrification efforts in the developing world.

Project Leads: Victoria Plutshack, Jonathon Free, Robert Fetter

View the team's final project summary here

Watch the team's final presentation (on Zoom) here:

Disease Emergence and Richness in Primates

The Disease Emergence and Richness in Primates team uses existing databases to quantify parasite richness across primates and to identify ecological predictors of parasitism. By integrating phylogenetic generalized least squares regression and network based approaches, the team ultimately aims to predict missing interactions between primates and parasites, which, combined with exploring ecological predictors, will provide better capabilities for identifying emerging infectious diseases in humans.

Project Leads: Jim Moody, Charles Nunn

Project Manager: Marie Claire Chelini

Click here to view the team's final project summary

ABOUT-US – A BOundary Update Tool for Utility Services

We all need water to survive but how many of us really know where our water comes from? Team 3 has created a functioning website from scratch to give consumers more easily accessible information about who provides their water and how supply looks in relation to the past 30 years.

Project Leads: Megan Mullin, Lauren Patterson

Watch the team's final presentation (on Zoom) here:

Project Manager: Kyle Onda

Computational Tools to Improve Healthy and Pleasurable Eating in Young Children

Our project is about building a food recommendation system for Avoidant/Reactive Intake Disorder (ARFID) patients and understanding the relationship between ARFID and clinical variables. Our stakeholders include young picky eaters and their parents, as well as clinicians who work with ARFID patients. We created an interactive visualization for ARFID patients to encourage them to explore different foods and also built visualization to represent the relationship between ARFID and clinical variables.

Project Leads: Guillermo Sapiro, Nancy Zucker

Project Manager: Julia Nichols

View the team's final project presentation slides here

Watch the team's final presentation below:

When Black Stories Go Global: Analyzing the Translation of African-American Literature and Film

Led by Dr. Eva Wheeler, this project considers how racial language in African American literature and film is rendered for international audiences and traces the spread of these translations. To address the study’s primary questions, the team analyzed a preliminary dataset and explored the relationship between translation strategy and different categories of racial language. The team also conducted a macro-level analysis of the linguistic, temporal, and geographic spread of African American stories using the IMDB and WorldCat databases. We have found a large amount of variation in how African American stories are rendered, which can in part be explained through a social scientific lens.

Human Activity Recognition using Physiological Data from Wearables

Traditional Human Activity Recognition (HAR) utilizes accelerometry (movement) data to classify activities. This summer, Team #4 examined using physiological sensors to improve HAR accuracy and generalizability. The team developed ML models that are going to be available open source in the Digital Biomarker Discovery Pipeline (DBDP) to enable other researchers and clinicians to make useful insights in the field of HAR.

Project Lead: Jessilyn Dunn

Project Manager: Brinnae Brent

Click here to view the project team's project poster

Watch the team's final presentation (on Zoom) below:

Getting Granular on Social Determinants of Health

Social and environmental contexts are increasingly recognized as factors that impact health outcomes of patients. This team will have the opportunity to collaborate directly with clinicians and medical data in a real-world setting. They will examine the association between social determinants with risk prediction for hospital admissions, and to assess whether social determinants bias that risk in a systematic way. Applied methods will include machine learning, risk prediction, and assessment of bias. This Data+ project is sponsored by the Forge, Duke's center for actionable data science.

Project Leads: Shelly Rusincovitch, Ricardo Henao, Azalea Kim

Project Manager: Austin Talbot

Investigating oil and gas production in the United Kingdom

Aaron Chai (Computer Sciece, Math) and Victoria Worsham (Economics, Math) spent ten weeks building tools to understand characteristics of successful oil and gas licenses in the North Sea. The team used data-scraping, merging, and OCR method to create a dataset containing license information and work obligations, and they also produced ArcGIS visualizations of license and well locations. They had the chance to consult frequently with analytics professionals at ExxonMobil.

Research

Research

Rhodes Information Initiative at Duke

Participate

Research

News & Events

Stay Connected

Search form