Photo of Miranda, Fabio

Fabio Miranda

Assistant Professor

Department of Computer Science

Contact

Building & Room:

1120 SEO

Address:

851 S. Morgan St, MC 152, Chicago, IL, 60607

Office Phone:

(312) 996-3422

CV Link:

Fabio Miranda

Related Sites:

About

I am interested in developing techniques that allow for the interactive visual analysis of large-scale data, combining methods from visualization, data management, machine learning, and computer graphics. In particular, I focus on how visual data analytics can help address different problems cities face by integrating data on different resolutions and from different sources.

I have worked closely with domain experts from different fields and the outcome of these collaborations included not only research published in Vis, DB, and AI venues, but also systems that were made available to experts in academia, industry and government agencies. My work has also received extensive coverage from different media outlets, including The New York Times, The Economist, Architectural Digest, Curbed, among others.

 

Prospective students: send me an email if you are interested in conducting and publishing research in the areas of data science, human-computer interaction and visualization, including:

  • Visual analytics, including interactive visual data analysis.
  • Data structures and indexing techniques for big data visualization, making use of new advancements in GPUs architectures.
  • Urban analytics, harnessing data sets of different types (images, land use information, 3D building geometry, etc.) to address concrete city problems.
  • Applied machine learning, including image feature extraction and graph neural networks.

(See my website for more details, including open positions.)

Selected Publications

Urban Mosaic: Visual Exploration of Streetscapes Using Large-Scale Image Data
Fabio Miranda, Maryam Hosseini, Marcos Lage, Harish Doraiswamy, Graham Dove, Claudio T. Silva
CHI 2020

Learning Geo-Contextual Embeddings for Commuting Flow Prediction
Zhicheng Liu, Fabio Miranda, Weiting Xiong, Junyan Yang, Qiao Wang, Claudio T. Silva
AAAI 2020

Shadow Accrual Maps: Efficient Accumulation of City-Scale Shadows over Time
Fabio Miranda, Harish Doraiswamy, Marcos Lage, Luc Wilson, Mondrian Hsieh, Claudio T. Silva
IEEE Transactions on Visualization and Computer Graphics, 2018

Spatio-Temporal Urban Data Analysis: A Visual Analytics Perspective
Harish Doraiswamy, Juliana Freire, Marcos Lage, Fabio Miranda, Claudio T. Silva
Computer Graphics and Applications, 2018

Time Lattice: A Data Structure for the Interactive Visual Analysis of Large Time Series
Fabio Miranda, Marcos Lage, Harish Doraiswamy, Charlie Mydlarz, Justin Salamon, Yitzchak Lockerman, Juliana Freire, Claudio T. Silva
Computer Graphics Forum, 2018

Interactive Visual Exploration of Spatio-Temporal Urban Data Sets using Urbane
Harish Doraiswamy, Eleni Tzirita Zacharatou, Fabio Miranda, Marcos Lage, Anastasia Ailamaki, Claudio T. Silva, Juliana Freire
SIGMOD’18: 2018 International Conference on Management of Data

TopKube: A Rank-Aware Data Cube for Real-Time Exploration of Spatiotemporal Datasets
Fabio Miranda, Lauro Lins, James Klosowski, Claudio T. Silva
IEEE Transactions on Visualization and Computer Graphics, 2017

Urban Pulse: Capturing the Rhythm of Cities
Fabio Miranda, Harish Doraiswamy, Marcos Lage, Kai Zhao, Bruno Gonçalves, Luc Wilson, Mondrian Hsieh, Claudio T. Silva
IEEE Transactions on Visualization and Computer Graphics, 2017

Publication Aggregators

Notable Honors

2018, SIGMOD Best Demonstration Award, SIGMOD

2018, Pearl Brownstein Doctoral Research Award, New York University

Education

Ph.D., Computer Science, New York University, 2018.
M.S., Computer Science, Pontifical Catholic University of Rio de Janeiro (PUC-Rio), 2011.
B.S., Computer Science, Federal University of Minas Gerais (UFMG), 2009.

Research Currently in Progress

  • Visualization of Probability Distributions of Geographical Data
  • Interactive Exploration of Large Image Databases
  • Automatic Assessment of Sidewalk Quality from Street-level Images
  • Urban Navigation in Virtual Reality
  • Interactive Profiling of City Land Use Evolution
  • Visual Data Exploration through User-Steerable Projections
  • Commuting Trip Distribution Modeling using Graph Neural Network