A team of computer science and software engineering students and faculty design a mobile app and data management solution to improve the structural integrity of vulnerable school buildings
SAN LUIS OBISPO – The Cal Poly Digital Transformation Hub (DxHub) powered by Amazon Web Services (AWS) and a team of Cal Poly students built a mobile app for the World Bank to help improve school safety in developing countries, planning to reduce costs and time by 50%.
Millions of children’s lives and billions of dollars worth of infrastructure are at stake as disasters such as earthquakes and cyclones threaten to collapse more than a million school buildings in low-income countries or intermediary. According to World Bank figures, around 875 million children and teachers could be injured or die in damaged school buildings. In addition, when schools close following disasters, there are indirect losses as students are deprived of learning opportunities, further compounding the impacts.
The cutting-edge technology was developed by the DxHub, using AWS cloud-based tools, for the World Bank’s global Safer Schools program (under the Global Facility for Disaster Reduction). disasters and recovery). A multidisciplinary team of undergraduate and graduate students and Professor Franz J. Kurfess worked with DxHub officials to create the mobile phone app design and deep learning computer vision model . The model simplifies how different types of school buildings vulnerable to natural disasters are identified to accelerate risk-based response and investment planning to make schools safer at scale.
The app design, automated data management solution and deep learning model have received international recognition from the Public Sector Innovation Observatory, a flagship initiative of the Organization for Cooperation and of economic development based in Paris. The OECD, which has existed for 60 years and has 38 member countries, supports and advises governments in implementing innovative approaches to transform their public sector.
The solution’s design is the result of an academic partnership between the DxHub and the World Bank, one of the world’s largest sources of finance and knowledge for developing countries. The World Bank helps developing countries share and apply knowledge and innovative solutions to solve challenges in all major areas of development to end poverty and achieve shared prosperity, through a wide range of financial products and technical assistance.
The app design and deep learning computer vision model will help the Global Program for Safer Schools (GPSS) advance its agenda with scalable and efficient data solutions to facilitate strategic prioritization of investments governments based on evidence on the vulnerability of school buildings.
Faculty and students from DxHub and Cal Poly have been called in to help meet the challenge of developing school infrastructure benchmark data. There is a lack of basic data on the structural characteristics of school buildings in developing countries and no efficient way to collect, update and manage such a large amount of data on a national scale. Specifically, collecting field data across large geographic areas and labeling photographic data is time-consuming and expensive to perform in tens of thousands of schools.
The DxHub welcomed the opportunity to work with students to address this important and critical challenge.
“Our partnership with the World Bank enables Cal Poly students to innovate and solve problems in ways that make a real impact,” said DxHub Director Paul Jurasin. “This app design is just one example of the solutions we provide that can make a meaningful difference in the world, and we greatly appreciate the recognition of our collaboration.”
This month, Kurfess and his IT class presented the latest iteration of the solution design, which the GPSS team can now use as a template for field testing.
“Partnering with Cal Poly and DxHub helped us explore an AI-powered solution to address the national school infrastructure data gap by leveraging a team of talented young minds from multidisciplinary backgrounds” , said Fernando Ramirez Cortes, leader of the GPSS work team. “This approach will not replace traditional field surveys by qualified personnel but will complement more detailed assessments on a representative sample. By drawing conclusions at scale, the AI solution avoids having to perform these conventional assessments across the entire portfolio and is expected to reduce time and expense by 50%. »
This month’s final model demonstration caps off two years of research and development by multidisciplinary teams, including a virtual student exchange with Munich University of Applied Sciences, also part of the AWS Cloud Innovation program. Centers. The teams examined the use of artificial intelligence technologies for various aspects of making schools safer, creating an easy-to-use mobile app design to identify vulnerable school buildings most in need of intervention. Using the app, photos of school buildings are uploaded to the cloud where an AI deep learning algorithm determines the key vulnerability characteristics of each structure – building type, height and structural system.
A skilled engineer remotely reviews the initial results for accuracy and in doing so, refines the deep learning model to continuously improve the quality of the results. From there, the engineer’s findings are passed on to decision makers who can quickly prioritize investments for the most vulnerable school buildings.
For the students involved, including DxHub student employees Ashley Choi, a sociology and political science from San Mateo, Calif., and Elisa Horta, a mechanical engineer from Santa Clara, Calif., this project provides an educational experience Learn by doing as they graduate, ready to move into careers in industry.
“This project was a great opportunity to accelerate my learning in a real environment,” said Sydney Nguyen, a Cal Poly alumnus (Architecture and Ethnic Studies, ’20) from Oakland, Calif. “I was particularly drawn to the social impact of this project, with learning opportunities to use design and technology to help marginalized communities locally and globally.”
In addition to recognition from the OECD Public Sector Innovation Observatory, Kurfess and team presented at the 128th Annual Conference of the American Society for Engineering Education and were also recognized as half- SAFE STEPS D-Tech (Disaster Tech) Award Finalists for Innovative Technology. solutions that save lives before, during and after natural disasters.
The design for this solution can be found at:
The Public Sector Innovation Observatory case study is available at:
About the Cal Poly Digital Transformation Center
Cal Poly’s Digital Transformation Hub (DxHub) was one of the first collaborations between Amazon Web Services (AWS) and an educational institution focused on innovation and digital transformation. While providing students with real-world learning experiences, the DxHub applies proven innovation methodologies in combination with deep public sector subject matter expertise and AWS technology expertise to solve challenging problems. in a way not previously considered. For more information, visit https://dxhub.calpoly.edu.
About Cal Poly
Founded in 1901 and part of the renowned California State University system since 1960, Cal Poly is a comprehensive, four-year, nationally ranked polytechnic public university located in San Luis Obispo, California. Known for its Learn by Doing approach, small class sizes, and open access to expert faculty, Cal Poly is a distinct learning community whose nearly 22,000 academically motivated students enjoy an unparalleled hands-on educational experience that prepares them lead a successful personal and professional life. .
Top: Damaged School 1 — A school suffered extensive damage in a 7.8 magnitude earthquake that rocked Nepal on April 25, 2015, collapsing multi-storey structures in Kathmandu and causing avalanches and landslides in the Himalayas. Around 9,000 people were killed and more than 22,000 were injured.
Photo courtesy of The World Bank
Second photo from top: School exterior — An official takes a picture of the school in the Kyrgyz Republic, the landlocked mountainous country in Central Asia, as part of a pre-disaster structural assessment.
Photo courtesy of The World Bank
Third photo from top: SaferSchoolsApp – A team of Cal Poly students designed a mobile app for the World Bank to help improve school safety in developing countries, with plans to reduce costs and le 50% time. From left to right, Nicholas Hansen (Computer Science, 2022), Zachary Cipolla (Computer Science, 2022), Elisa Horta (Mechanical Engineering, 2023), Melissa Nardone (Computer Engineering, 2022) and Professor Franz Kurfess meet remotely with the global program of the World Bank for the Safer Schools team.
Photo of Joe Johnson | Cal Poly
Fourth photo from top: Overview — A multidisciplinary team of Cal Poly students, led by Professor Franz J. Kurfess of the Department of Computer Science and Software Engineering, worked with DxHub officials to design a mobile phone app and deep learning computer vision model. The model simplifies how different types of school buildings vulnerable to natural disasters are identified to accelerate risk-based response and investment planning to ultimately make schools safer at scale.
Photo courtesy of The World Bank
April 28, 2022
Contact: Matt Lazier
805-756-7109; [email protected]