Urban renewal was a national initiative from 1960s through 70s aimed at improving so-called “blighted” areas, and resulted in the displacement of many vibrant communities. While the underlying mechanisms of urban renewal have been examined, there have been very few data-driven, evidence-based studies that take into account the histories and interests of former residents. The “Human Face of Big Data” project started as a digital curation effort to design and develop a web-based, big data platform that provides insights and analytics into the mechanisms of this process.
The Cycle Atlanta project aims at creating sensor systems that allow a bike to "see" its environment and collect data as a participatory effort so that we can help the City of Atlanta to make informed decisions about biking infrastructures. Specifically, a sensor box equipped with sonars, lidars, PM sensors, gas sensors, gyroscope, accelerometer, and others was developed to detect environmental factors that can give rise to cyclists' stress level. I participated in this project as a Data Science for Social Good (Atlanta's DSSG) Summer fellow in 2017.
Defining neighborhood boundaries within a city is a complex and often subjective task. Neighborhoods boundaries are defined by the people that visit and live in the region, and activities that occur within those boundaries. Depending on the individual or group activity being conducted, these boundaries can change substantially. Transportation and human mobility patterns offer a novel basis on which to explore and delineate neighborhoods.
"Poverty maps" are designed to simultaneously display the spatial distribution of welfare and different dimensions of poverty determinants. The plotting of such information on maps heavily relies on data that is collected through infrequent national household surveys and censuses. However, due to the high cost associated with this type of data collection process, poverty maps are often inaccurate in capturing the current deprivation status.
This project aims to build a map-based platform that can be used in presenting historical documents of the nation-wide, urban renewal project in 1960's and 70's to provide easy-to-use interfaces that can be used by former residents, archivists, researchers, and citizens; and ultimately to reconstruct a virtual neighborhood where people can share their memories.
Over the past four years, teams of archivists have digitized portions of National Archives RG195: General Records of the Home Owners’ Loan Corporation [HOLC]. The records include surveys, memorandums, and maps of American neighborhoods in the 1930’s. Now that the records are available digitally, students and faculty members are working to curate the collection and “data-fy” the information contained within.
Social media has provided a huge amount of user-generated data in capturing urban dynamics. Among them, place-level human behavior has been largely detected through people’s check-in records at certain places. Conventionally, places are characterized by a set of pre-defined features, often specified by the owner of the places. In this paper, we argue that capturing socially-meaningful features and dynamics of an urban place may also be done by analyzing human activity traces.
The Center for Open Data Enterprise is a non-profit organization that aims to maximize the value of open data as a public resource that anyone can use. As a means to promote the impact and value of using open data, the center designed and developed the Open Data Impact map. As a Data Science & Technology Fellow at the Center for Open Data Enterprise, I have worked on the Open Data Impact Map, which is a searchable, centralized database of open data use cases from around the world. The map shows the distribution of organizations in the world that make use of open data.
This paper describes innovative partnerships: university - federal agency (between the University of Maryland and the Office of Innovation at the National Archives and Records Administration - NARA) and university - industry (between the College of Information Studies or “iSchool” at the University of Maryland and Archive Analytics Solutions Ltd.) where we are developing automated scalable workflows that involve digitization, OCR, information extraction, and linking into interactive maps and graph databases, and where digital preservation and archiving are performed using an innovative NoSQ
Information accessibility problems include diverse types of human- and system-driven barriers that make it difficult for individuals to access desired information. These issues have been studied in two main streams: (1) a human-centered view based on the understanding of individual-level characteristics such as physical impairment and economic status; and (2) a technology-focused view that emphasizes on system factors such as the information filtering techniques and interface designs.