2023 Capstone Projects

The CUSP Capstone Program gives our graduate students the opportunity to have an impact on critical urban issues while continuing to develop their data science skills and honing their public policy expertise. This year, projects have been grouped into three categories: urban health, urban environment, and urban infrastructure. Stay tuned throughout the spring and summer semesters to hear more about how our 2023 capstone projects are progressing. Thanks to all who applied to participate!

Urban Health

Affordability, Scalability, and Accessibility of In-Home and Community-Centered Soft Robotic Systems for Tele-Rehabilitation

Project Sponsor

Project Abstract

This capstone will explore the affordability (and therefore accessibility) of soft robotics for assistive technologies – with the goal of developing technology that can be brought out of the lab and into real-world environments throughout the city, such as in people’s homes or in communal robotic gyms. This is part of a larger effort to democratize healthcare for the well-being of all citizens. This capstone is not about building robots – it’s about using data and literature to assess the viability of affordable solutions for novel soft robotic technologies.

At the Intersection of Head and Eye Control in Patients with Blindness and Low Vision

Project Sponsors

Project Abstract

Understanding the role of eye movements and their coupling with other body movements when acquiring navigation-relevant visual information is critical, especially for individuals with navigation challenges. This project will deploy a head-mounted eyetracker to examine eye-head synergies in sighted individuals and people with blindness/low vision to assess the presence and nature of any differences in the saccadic main sequence and the extended eye-head saccadic main sequence. We predict that the degree of decoupling will correlate with the degree and type of visual impairment (central/peripheral). Results will advance our knowledge of integrated motor control for the visually impaired in urban navigation.

Improve Public Guidance to Natural Disasters

Project Sponsors

  • Aidan Mcinerney, Head of Data Science, GHD
  • Dario Feliciangeli, Transport Market Leader, GHD
  • Simon Babes, EMEA Market Development Leader – Advisory, GHD

Project Abstract

Measuring response to public guidance during incidents of wildfires or major storms.

Increasing Usability of Bipedal Robots for Urban Environments Through Penguin Data Analysis

Project Sponsors

Project Abstract

The goal of this capstone project is to determine fundamental principles of locomotion on low friction terrains through data analysis on penguins and penguin-robots. Low friction terrains are commonly found in urban environments such as icy sidewalks and freshly mopped floors. This project aims to understand how penguins navigate those terrain types and how those methods can be implemented on robots. Statistical analysis and possibly machine learning will be used based on the level of experience of the students.

Interactions Among Echo Chambers in Social Media

Project Sponsors

Project Abstract

The emergence of echo chambers across online social networks is boosting polarization of individual users regarding sensitive topics such as gun control, urban violence, racism, abortion, vaccinations, and police brutality. There is limited understanding of the influential nodes within such homogenous communities, and how echo chambers interact with each other. In this project, we will leverage tools from network science to shed light on the structures of echo chambers and detect their “leader” content creators. Results will help social media platforms in developing feed algorithms tailored towards dismantling chambers that are incubators for extremely polarized opinions affecting our society.

Multimodal Machine Learning for Spatiotemporal Identification of Sound Sources in the NYC Subway System

Project Sponsors

  • Iran R. Roman, Postdoctoral Associate, NYU CUSP
  • Juan P. Bello, Professor of Music Technology and Computer Science & Engineering, NYU CUSP

Project Abstract

The NYC subway has a very complex soundscape that can be loud, exposing individuals riding and living nearby to harmful sound levels. The factors that give rise to loud levels of sound have not been carefully characterized and as a result it is not clear why some places and/or times of the day are louder than others. In this project, we will use machine learning on real video and audio recordings, collected in the NYC subway, to answer the question: how do station structure, train mechanics, and human activities in the NYC subway contribute to harmful sound levels?

Urban Environment

Building a Global Standard for Future Built Environment Data

Project Sponsors

  • Tyce Herrman, Head of Product, inCitu
  • Dana Chermesh-Reshef, Founder & CEO, inCitu

Project Abstract

Most people have no reliable, trustworthy tools to help them envision the future of their urban home. Plans for new developments are inaccessible or opaque, with data scattered in marketing documents, filings, permits, databases, maps, and more.

inCitu is on the mission to make urban development information transparent, tangible, and accessible to promote a more equitable city planning process and empower residents in the process of urban change.

In this Capstone project students will review different city planning datasets and resources in varied US urban areas to create a gold standard for urban development data collection and management.

Comparing How Representative Public Feedback is to the Community

Project Sponsors

Project Abstract

Resident feedback is a core tool of municipalities, and is often a required step for projects large and small. Yet it isn’t always clear how representative of the “community” our respondents are. We aim to develop a comparative tool which allows policymakers to assess how responsive public feedback is to their community, at many scales.

FloodNet - Computer Vision for Urban Street Flood Detection

Project Sponsors

  • Charlie Mydlarz, Research Associate Professor, NYU CUSP, FloodNet
  • Chen Feng, Assistant Professor of Civil and Urban Engineering & Mechanical Aerospace Engineering, NYU CUSP 

Project Abstract

In NYC, sea level rise has led to a dramatic increase in flood risk, particularly in low-lying and coastal neighborhoods. Urban flood water can impede pedestrian and vehicle mobility, and also can contain a diverse array of contaminants, including fuels, raw sewage, and industrial/household chemicals. For this capstone project, the team will train, test and deploy computer vision (CV) and deep learning (DL) models for the detection of street flood events. Existing labelled datasets will be used for training. In addition, an unlabelled NYC street image dataset will be provided for labelling and training of a NYC centric model.

Machine Learning Mapping of Heat Risk in Cities Using Satellite and Ground Data in Google Earth Engine

Project Sponsor

Project Abstract

Cities are exposed to higher temperatures due to the extensive presence of man made heat sources and climate change, the latter resulting in the increase of the duration, strength and frequency heat waves. Estimating heat risk through a synthetic methodology that combines satellite images and ground data and uses machine learning for cluster analysis based on landscape, urban and social parameters is important in order to (a) recognize which areas and which populations are disproportionately exposed to heat risk (“extreme heat injustice”), especially in the event of heat waves (b) to define measures to mitigate heat risk and (c) to support urban resilience to climate extremes.

Understanding the True Cost of Vacant Properties in Baton Rouge

Project Sponsor

  • Manny Patole, Community Engagement Lead, Linking Flood Resilience to Urban Reinvestment in Baton Rouge
  • Dr. Rebeca de Jesus Crespo, Department of Environmental Sciences, LSU

Project Abstract

Vacant and abandoned properties represent a financial burden to municipalities, and a health and safety hazard to communities. Returning these vacant properties back into productive use is of great economic interest in terms of tax revenue, the real-estate and commercial activity they could bring to an area, and also in terms of lowering maintenance cost of waste removal, and green space management, which often falls into the hands of municipalities. These costs have not fully documented or understood for Baton Rouge, LA.

Urban Infrastructure

Dashboard for Power Outage Forecasts for an Emergency Response to Hurricanes

Project Sponsors

Project Abstract

Hurricanes damage power systems and cause power disruptions for millions of people. This project will inform utility companies and communities about the power outage risks before hurricanes makes an impact. The project’s main goal is to visualize forecasted power outages through a dashboard by developing a pipeline that utilizes National Oceanic and Atmospheric Administration weather forecasts to predict outages before a storm impacts. The outcome of this project could inform utility companies to take appropriate measures, e.g., installing backup power and placing their crews ahead of a storm to recover the power system rapidly.

Data Driven Model for Medium Voltage Cable Fault

Project Sponsors

Project Abstract

The currently ongoing energy transition requires a significant increase in the resilience of electrical distribution grid. Moreover the failure rate upon the grid is growing in the last years, due to the increase in extreme weather conditions. Consequently, it is crucial for the electrical distribution system operator (DSO) to better understand the grid failure phenomena in order to optimally drive preventive interventions. In this project, we seek to carry out a model for the fault phenomenon which identifies its dependence on the grid’s constitutive parameters, operational variables, and external causes (weather, grid load, etc), exploiting the information collected in the urban area of Rome.

Developing an AI-Based Image Classifier for School Infrastructure Baseline Data Collection in Large Scale Disaster Risk Analysis

Project Sponsors

Project Abstract

This project will develop a risk-informed classification system to support AI computer vision algorithms for assessing seismic vulnerabilities in schools. The project will be led by the World Bank’s Global Program for Safer Schools (GPSS), the NYU Disaster Risk Analysis Lab, and the NYU AI4CE. The project’s main goal is to develop a simplified vulnerability classification system based on existing detailed taxonomy from the Global Library of School Infrastructure (GLOSI), to support AI-based computer vision tools to reduce structural vulnerability data collection time and costs in large building portfolios. We envision that the simplified classification will enable more reliable AI computer vision tools to empower communities to be engaged in governments’ disaster risk management efforts more easily, make risk analysis more accessible and informed by up-to-date baseline information worldwide and guide large-scale school safety and resilience investments more efficiently.

Assessing Coping Capacity: Understanding the Resilience of NYC Communities to Coastal Flooding

Project Sponsor

Project Abstract

New York City has long been exposed to disastrous floods causing billions of dollars in damage. Better policies could mitigate the consequences of catastrophic events, but agreement on which actions to implement and which areas to prioritize is not always easy to achieve. Policymakers need information on potential flood-related losses to allocate the proper resources for mitigation measures. This project aims to create a digital model of New York City that can estimate potential disruption for given flood scenarios. It will incorporate diverse data on buildings, transportation and social vulnerability, to provide a broad perspective on risk to city government agencies and residents.

Follow the Data & Money: Mapping NYC's Unregulated Surveillance Economy to Expand Local Governance Solutions

Project Sponsors

Project Abstract

NYC is a key site of technological innovation—including an expansive surveillance economy. Much of this technology is acquired by City agencies through contracts with private corporations. By following data and money trails, this project illuminates the scale of the unregulated surveillance economy and how NYC’s procurement system—an antiquated and opaque web—deeply impacts urban life. Specifically, we explore how technology procurement expands discriminatory policing power and undermines community-centered governance. Combined with qualitative research, our data analysis illustrates how the surveillance economy exacerbates racism and inequality. We are developing recommendations for community-based governance mechanisms to make procurement more accountable to all residents.

Low-Power Computer-Vision-Based Pedestrian Counting Research II

Project Sponsor

Project Abstract

Many City agencies are involved in the use, planning, and design of public space but good data on pedestrian flows can be hard to come by. Manual counts take coordination and planning as well as staff costs. Computer-vision (CV) counting technologies are being tested in the city now but it is already clear that the infrastructure requirements (tapping into electricity and mounting to light poles) will be a limiting factor in using this technology more broadly and particularly for shorter-term studies where the infrastructure investment is not worth the time and effort. A low-cost, battery-powered CV sensor can help fill the data gap and allow agencies to utilize privacy-protected automated counts in short-term deployments with minimal infrastructure requirements.

This is the phase 2 of the project that continued from the previous CUSP capstone project, and the focus of phase 2 is (1) to scale up the project with more real-world data collection and analysis; and (2) to improve our data visualization dashboard.

National Broadband Tool

Project Sponsor

Project Abstract

Access to broadband has changed how people live and do business. The COVID-19 pandemic has only exposed the existing health, economic, and social challenges within the county, and have highlighted the need to be prepared for such events in the future. Governments of all levels are tasked with easing the burden that citizens and local businesses face. Access to “good” broadband has never been more important than that in the last 2 years. NTIA and FCC’s broadband deployment programs have had socio-economic impacts on the cities in many ways. With the infrastructure bill passed, focus on getting broadband to every corner of the country is necessary and needed.

Real-Time Augmented Reality Mobile App to Find Vehicles in a Crowded Parking Lot

Project Sponsors

  • Varun Adibhatla, Head of Data Science and Analytics, NYCSBUS
  • Holly Orr, Chief Information Officer, NYCSBUS
  • Cristopher Soto, Data Engineer, NYCSBUS 

Project Abstract

NYCSBUS operates a fleet of 1,000 vehicles across 5 yards. A yard can have 250 vehicles at a time. “Morning pull outs” from the yard are a crucial time to ensure on time service. While each vehicle is equipped with a GPS device, the act of finding a bus in a crowded yard can be daunting. Our staff need to be able to identify buses quickly to ensure smoother morning pull outs. An augmented reality mobile app that integrates with our telematics API would allow staff to quickly point a camera and search for a vehicle with minimal input.

Reverse Engineering to Estimate Subsurface Utility Infrastructure Density for Financing Smart City Infrastructure

Project Sponsors

Project Abstract

This capstone will develop a methodology to estimate subsurface utility infrastructure density (3D volumetric approach) within NYC from NYC DCP surface density maps, USGS Lidar, and NYC DOT street geometry data for public right of way area calculations (and possibly estimating subsurface densities in Westchester and Nassau Counties for comparison purposes in a similar manner), to permit a subsequent estimation of a utility pricing gap within NYC to support development of revenue sources to finance utilidors.

Understanding the Intensity of Community Surveillance in Brooklyn Through Public Datasets

Project Sponsors

Project Abstract

How do we quantify the intensity of surveillance that neighborhoods across Brooklyn are subjected to by the presence of surveillance cameras? Which communities are disproportionately impacted by this surveillance load? While the indicator variable is surveillance cameras for this research, we hope to develop a more general methodology that can be applied to other datasets describing other forms of surveillance technology – like facial recognition, geolocation tracking, or body-worn cameras – in the future.

Using Telematics Data to Evaluate Breakdown Risk for NYC School Buses

Project Sponsors

  • Varun Adibhatla, Head of Data Science and Analytics, NYCSBUS
  • Holly Orr, Chief Information Officer, NYCSBUS
  • Cristopher Soto, Data Engineer, NYCSBUS 
  • Ed Driscoll, Chief Fleet and Facilities Officer, NYCSBUS 

Project Abstract

NYCSBUS is a non-profit school bus company that seeks to provide outstanding service to families and schools in New York City while innovating in student transportation. NYCSBUS operates a fleet of 1000 school buses transporting 9000+ students across the NYC Metro Area. A majority of these students have special needs. NYCSBUS vehicles are equipped with GEOTAB, a device that tracks vehicle location, engine diagnostics and other telematics. NYCBUS wants to use telematics data to detect patterns and evaluate vehicle breakdown risk in order to develop proactive maintenance programs. The overall goal is to reduce vehicle breakdowns.

Utilizing a Unique Dataset to Advance Affordable Housing

Project Sponsors

Project Abstract

The capstone team will clean a user-entered dataset and assist NCST in using it to advance the mission of affordable housing and neighborhood stabilization.

Vehicle Allocation Modeling (V.A.M.) - Optimizing the logistics behind a free-flow carsharing in Milan, Italy

Project Sponsor

Project Abstract

Sharing mobility has become one of the emerging transport modes, but seldom is its planning entrusted to private operators and not seen as a major vector of urban mobility.

The vehicle allocation greatly influences the benefits of the whole system, since it is linked to the potential accessibility and the opportunity to substitute and complement other less sustainable modes.

In this framework, the role of planning is paramount, and the operational design behind a free-flow system has the opportunity to be assessed at the intersection between the utilization patterns of the vehicles and the characteristics of the urban environment.

Virtual and Augmented Reality for Community Preparedness to Disasters [Part II]

Project Sponsors

Project Abstract

This project will create physically realistic virtual and augmented reality (VR and AR) environments that represent extreme events such as wildfires, floods, landslides, winds, and earthquakes affecting our communities. The project will use these environments to show how resilient infrastructure and response preparedness in a disaster can significantly reduce the probability of physical and human losses. The virtual environment will then be deployed to VR/AR devices for egocentric and immersive viewing. The project will be led by the NYU Immersive Computing Lab, NYU Disaster Risk Analysis Lab, and the World Bank’s Global Program for Safer Schools (GPSS). The project’s main goal is to raise awareness and prepare our communities to respond to extreme events using immersive realities to enhance the effectiveness of drills, such as evacuating during floods.