Kazi Shahrukh Omar

Research Assistant at Electronic Visualization Laboratory (EVL) advised by Dr. Fabio Miranda. Visit my profile at EVL's website here.

CS PhD student @ University of Illinois Chicago.

My research leverages skills in visualization & visual analytics, big data analysis, and applied machine learning. Specifically, I focus on utilizing these skills within urban planning and health informatics, aiming to enhance the ability of domain experts to efficiently analyze large-scale data and uncover complex patterns through advanced visual analytics systems. My work also involves open-sourcing projects to foster further research in these areas, that include: (1) VIGMA, a comprehensive system for gait data processing, analysis, and visualization, and (2) Deep Umbra, an accumulated shadow computation technique along with visual analytics system and shadow dataset for over 100 cities.

Outside of my academic work, I enjoy playing guitar, listening to music, and a little bit of reading. I also love watching series and movies, as well as traveling, although I've had fewer opportunities to travel lately. Recently, I've developed a growing interest in board games and anime.

News

Oct 2024	Attended CLEETS Fall School on decarbonizing road transportation with global experts (Certificate). 🌱
Aug 2024	Open sourced VIGMA, a framework for handling the workflow of gait data processing, analysis, and visualization.
Aug 2024	Began role as a Research Assistant with the CLEETS team, contributing to decision support tools for cross domain urban planning. ♻️
May 2024	Joined as a full-time Research Assistant for Summer 2024 at the CogMoBal Lab of Applied Health Sciences Dept, UIC, working on developing an open-access visual analytics system for gait data processing, analysis, and visualization.
Feb 2024	“Deep Umbra: A Generative Approach for Sunlight Access Computation in Urban Spaces” has been accepted for publication in the journal “IEEE Transactions on Big Data”. View the paper here.

Selected publications

Deep Umbra: A Generative Approach for Sunlight Access Computation in Urban Spaces

Kazi Shahrukh Omar, Gustavo Moreira, Daniel Hodczak, and 4 more authors

IEEE Transactions on Big Data, 2024

Abs Bib PDF

Sunlight and shadow play critical roles in how urban spaces are utilized, thrive, and grow. While access to sunlight is essential to the success of urban environment, shadows can provide shaded places to stay during the hot seasons, mitigate heat island effect, and increase pedestrian comfort levels. Properly quantifying sunlight access and shadows in large urban environments is key in tackling some of the important challenges facing cities today. In this paper, we propose Deep Umbra, a novel computational framework that enables the quantification of sunlight access and shadows at a global scale. Our framework is based on a conditional generative adversarial network that considers the physical form of cities to compute high-resolution spatial information of accumulated sunlight access for the different seasons of the year. We use data from seven different cities to train our model, and show, through an extensive set of experiments, its low overall RMSE (below 0.1) as well as its extensibility to cities that were not part of the training set. Additionally, we contribute a set of case studies and a comprehensive dataset with sunlight access information for more than 100 cities across six continents of the world. Deep Umbra is available at urbantk.org/shadows
@article{omar2024deep, title = {Deep Umbra: A Generative Approach for Sunlight Access Computation in Urban Spaces}, doi = {https://doi.org/10.1109/TBDATA.2024.3382964}, author = {Omar, Kazi Shahrukh and Moreira, Gustavo and Hodczak, Daniel and Hosseini, Maryam and Colaninno, Nicola and Lage, Marcos and Miranda, Fabio}, journal = {IEEE Transactions on Big Data}, year = {2024}, }
Crowdsourcing and Sidewalk Data: A Preliminary Study on the Trustworthiness of OpenStreetMap Data in the US

Kazi Shahrukh Omar, Gustavo Moreira, Daniel Hodczak, and 2 more authors

ASSETS UrbanAccess Workshop, 2022

Abs Bib PDF

Sidewalks play a pivotal role in urban mobility of everyday life. Ideally, sidewalks provide a safe walkway for pedestrians, link public transportation facilities, and equip people with routing and navigation services. However, there is a scarcity of open sidewalk data, which not only impacts the accessibility and walkability of cities but also limits policymakers in generating insightful measures to improve the current state of pedestrian facilities. As one of the most famous crowdsourced data repositories, OpenStreetMap (OSM) could aid the lack of open sidewalk data to a large extent. However, completeness and quality of OSM data have long been a major issue. In this paper, we offer a preliminary study on the availability and trustworthiness of OSM sidewalk data. First, we compare OSM sidewalk data coverage in over 50 major cities in the United States. Then, we select three major cities (Seattle, Chicago, and New York City) to further analyze the completeness of sidewalk data and its features, and to compute a trustworthiness index leveraging historical OSM sidewalk data.
@article{omar2022crowdsourcing, title = {Crowdsourcing and Sidewalk Data: A Preliminary Study on the Trustworthiness of OpenStreetMap Data in the US}, author = {Omar, Kazi Shahrukh and Moreira, Gustavo and Hodczak, Daniel and Hosseini, Maryam and Miranda, Fabio}, journal = {ASSETS UrbanAccess Workshop}, year = {2022}, }