SLU Innovation Challenge

Team Members

• Ruaa Al Juboori, MBChB, MPH, Ph.D. student
• Ucheoma Nwaozuru, Ph.D., Post Doctoral Fellow

Project Summary

As of May 6, 2021, the United States reported a total of 32.3 million cases of COVID-19 and over 570,000 deaths since the beginning of the pandemic. Reducing COVID-19 morbidity and mortality will require equitable distribution of vaccination and other prevention services. Yet, the national focus is on the big metropolitan regions with limited representation of rural counties. Many of these counties have larger minority populations. Some of these counties are showing spikes in the number of COVID-19 cases/deaths. Therefore, providing a balanced and nuanced analysis of the urban vs rural areas using Rural-Urban Continuum Codes (RUCC) will provide a more comprehensive picture of rural counties with the majority of Native American, Latino and Black populations.

This is a prototype/proof of concept to visualize health outcomes, particularly COVID-19 cases/deaths based to highlight rurality. We undertook an exploratory approach with no underlying theoretical framework, to provide a typology to understand if rurality matters in health outcomes. In the case of COVID-19 cases/deaths, information on the influence of location can inform tailored distribution strategies for COVID-19 vaccines and for other health outcome measures.

Team Members

• Laura Brugger, M.A., Ph.D. student
• Pedro Spindler-Ruiz, MPP, Ph.D. student

Project Summary

Latino voters have often been portrayed as a monolithic group, even though studies have shown that Latino voting patterns are not uniform and instead vary based on key socio-spatial characteristics such as education, class, region and country of origin, among many others. This inaccurate portrayal of a Latino voting group presents challenges for protecting voting rights among a growing electorate.

Through this project, we sought to gain a better understanding of variation in how Latinos voted in the 2020 presidential election through the creation of an open-source, interactive GIS visualization tool and by estimating socio-demographic characteristics at the precinct-level. We plan to use this tool to inform strategies that address the ecological fallacy and strengthen the Voting Rights Act for Latinos in the United States.

See the project's story map

Team Members

• Caleb Buffa
• Zach Phillips, Ph.D.

Project Summary

We can confirm the locations of explosions when there are people around, but what if nobody is around to witness an explosion, or worse: everyone in the explosion is killed and there is no reporting? We used the location of known explosions to create an app that estimates unknown, unconfirmed explosions. The app uses change detection statistics from known explosion events in the ACLED database to estimate the probability of an explosion in a user-selected location using Machine Learning and the Google Earth engine.

Team Members

• Akbar Fidahussain, Parks College of Engineering Aviation and Technology
• Mohammad Hadi, Parks College of Engineering Aviation and Technology
• Fauzan Hasanbasri, Parks College of Engineering Aviation and Technology
• Sarem-Alden Othman, Chaifetz School of Business

Project Summary

We sought to create a first-generation prototype of a cheaper alternative for cell towers using a balloon, mainly to be used during emergency situations when mainstream towers are down. We developed a battery-powered circuit to power and charge Arduino controlled RF receivers and transmitters to relay messages between first responders and victims of crisis.

We lifted the system into the air using a helium-filled balloon, with the payload beneath. Further improvements could be made by increasing structural integrity, using higher-end equipment, adding solar panels, and implementing a secure communication protocol.

Project Presentation

SLU 2020 Geospatial Innovation Challenge - Cheaper Alternative for Cell Towers Using Balloons

Team Members

• Mustafa Attallah, Parks College of Engineering Aviation and Technology
• Faten Mohammed, Parks College of Engineering Aviation and Technology
• Osama Mohammed, Parks College of Engineering Aviation and Technology

Project Summary

The proposed approach in this project was used to develop accident prediction models for a 4.91-mile segment of Interstate 270 in St. Louis, Missouri. The developed models will help the transportation agencies to proactively allocate their resources in anticipation of roadway accidents.

Random Forest, a Machine Learning Method built-in ArcGIS Pro was used to develop the prediction models. Overall, the performance of the Random Forest model's ability to estimate the location of traffic accidents was satisfactory and outperformed the performance measures reported for accident prediction outlined in the literature.

Project Presentation

SLU 2020 Geospatial Innovation Challenge - Public Space Management

Team Members

• Abhinav Kumar, Parks College of Engineering Aviation and Technology
• Eric Suter, Parks College of Engineering Aviation and Technology

Project Summary

With neural networks and machine learning becoming increasingly accessible, the technology can be applied for every-day use in public spaces to openly share useful information.

For our project, a small, self-sufficient internet-of-things device with a camera can determine whether a seat in a public space is currently occupied or predict when it will become vacant. Combined with geospatial data such as a 3D-scan of the space the device is in, the collected information can effectively communicate to end-users the availability of a certain location.

Project Presentation

SLU 2020 Geospatial Innovation Challenge - Public Space Management