Abstract:
In this presentation I will give a high-level overview of BALTO, a recently funded NSF SCC project that focuses on the design, development, deployment and evaluation of a privacy-respectful toolkit to identify and characterize the multi-factorial challenges typical of complex trips often times endured by low-income residents in Baltimore City; and to drive bottom-up, crowdsourced-informed actionable solutions via community conversations and a decision support system.
Case Study Summary:
- The scientific problem we tackled:
Lack of understanding of the barriers that low-income residents in Baltimore City face when using public transit. Collecting accurate data about their trips and their quality of service perceptions is challenging. We propose a toolkit to collect door-to-door mobility experiences and quality-of-service perceptions. - The computational methods we used:
The project combines quantitative machine learning approaches to model mobility experiences from spatio-temporal data so as to identify public transit barriers; together with focus groups to explore the design of data collection tools that are privacy respectful so as to enhance adoption. - The cloud resources we used:
Currently, we are developing the mobile app to carry out the door-to-door mobility experience collection. The app requires login and GPS/survey data storage. We are currently using AWS cognito, DynamoDB and S3 through AWS Amplify. - The differences we’ve observed between locally-provided and cloud-provided resources:
Many functionalities are already implemented in AWS and would require implementation from scratch in a locally-provided cloud e.g., app login.
Author Bio:
Vanessa Frias-Martinez is an associate professor in the iSchool and UMIACS, and an affiliate associate professor in the Department of Computer Science at the University of Maryland (UMD) where she also leads the Urban Computing Lab. Frias-Martinez's research areas are data-driven behavioral modeling and spatio-temporal data mining. Her research focuses on the use of large-scale ubiquitous data to model the interplay between human mobility patterns, social networks and the built environment. Specifically, Frias-Martinez develops methodologies to model and predict human behaviors in different contexts as well as tools to aid decision makers in areas such as poverty, natural disasters or urban planning. Before coming to UMD, she spent five years at Telefonica Research developing algorithms to analyze mobile digital traces. Frias-Martinez is the recipient of a National Science Foundation (NSF) CAREER Award and a La Caixa Fellowship. She received her PhD in Computer Science from Columbia University.
For further information:
RRoCCET21 is a conference that was held virtually by CloudBank from August 10th through 12th, 2021. Its intention is to inspire you to consider utilizing the cloud in your research, by way of sharing the success stories of others. We hope the proceedings, of which this case study is a part, give you an idea of what is possible and act as a “recipe book” for mapping powerful computational resources onto your own field of inquiry.
