AGArunav Gupta

Arunav Gupta

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Arunav Gupta has a total of 21 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Scaling pedestrian crossing analysis to 100 U.S. cities via AI-based segmentation of satellite imagery

    by Marcel E. Moran, Arunav Gupta, Jiali Qian, Debra Laefer

    Accurately measuring street dimensions is essential to evaluating how their design influences both travel behavior and safety. However, gathering street-level information at city-scale with precision is difficult given the quantity and complexity of urban intersections. To address this challenge in the context of pedestrian crossings — a crucial component of walkability — we introduce a scalable and accurate method for automatically measuring crossing distance at both marked and unmarked crosswalks, applied to America’s 100 largest cities. First, OpenStreetMap coordinates were used to retrieve satellite imagery of intersections throughout each city — totaling roughly three million images. Next, Meta’s Segment Anything Model was trained on a manually labelled subset of these images to differentiate drivable from non-drivable surfaces (i.e., roads vs. sidewalks). Third, all available crossing edges from OpenStreetMap were extracted. Finally, crossing edges were overlaid on the segmented intersection images, and a grow-cut algorithm was applied to connect each edge to its adjacent non-drivable surface (e.g., sidewalk, private property, etc.), thus enabling the calculation of crossing distance. This achieved 93% accuracy in measuring crossing distance, with a median absolute error of 2 feet 3 inches (0.69 meters), when compared to manually verified data for an entire city. Across the 100 largest U.S. cities, median crossing distances ranged from 32 feet to 78 feet (9.8 – 23.8m), with detectable regional patterns. Median crossing distance also displayed a positive relationship with the cities’ year of incorporation, illustrating in a novel way how American city planning increasingly emphasizes wider (and more car-centric) streets. These findings identified opportunities to improve pedestrian safety and increase walkability at multiple scales, from the individual block to the entire city.

  • Open Access

    Coloring Inside the Lines: The Jagged Legacy of the HOLC Neighborhood Risk Maps

    by Arunav Gupta

    There has been a large body of work exploring the discriminatory nature of the home mortgage risk maps produced by the Home Owners' Loan Corporation in the late 1930s. However, little attention has been paid to the question of whether these maps are still descriptive of racial residential boundaries in their cities 80 years after their creation. To address this gap, Markov Chain Monte Carlo, previously unutilized in the relevant literature, is employed to randomly generate many plausible alternative mortgage security maps. Then, the racial evenness of the HOLC maps and the generated maps is compared using Shannon's entropy. These findings indicate that the HOLC maps are significantly descriptive of the precise racial residential boundaries prevalent across eleven US cities in 2010. The methodology used here is highly modular and reproducible, allowing for future work measuring different outcome statistics, locations, and time periods.

  • Open Access

    Critique of: “A Parallel Framework for Constraint-Based Bayesian Network Learning via Markov Blanket Discovery” by SCC Team From UC San Diego

    by Arunav Gupta, John Ge, John Li, Zihao Kong, Kaiwen He, Matthew Mikhailov, Bryan Chin, Xiaochen Li, Max Apodaca, Paul Rodriguez, et al.

    Bayesian networks (BNs) have become popular in recent years to describe natural phenomena in situations where causal linkages are important to understand. In order to get around the inherent non-tractability of learning BNs, Srivastava et al. propose a markov blanket discovery-based approach to learning in their paper titled ”A Parallel Framework for Constraint-based Bayesian Network Learning via Markov Blanket Discovery.” We are able to reproduce both the strong and weak scaling experiments from the paper up to 128 cores, and verify communication cost scaling for all three algorithms in the paper. We also introduce methodological improvements to weak scaling that show the paper's findings are unique to the methodology and not the datasets used. Slight variations in performance were observed due to differences in datasets, core count, and job scheduling.


  • Critique of “MemXCT: Memory-Centric X-Ray CT Reconstruction With Massive Parallelization” by SCC Team From University of California San Diego

    by Xiaochen Li, Maximilian Apodaca, Arunav Gupta, Zihao Kong, Hongyi Pan, Hongyu Zhou, Mary Thomas, Martin Kandes, Zhaoyi Li, Mahidhar Tatineni, et al.

    In this article, we describe our efforts to reproduce results reported in the SC19 article by Hidayetoğlu et al. , titled “MemXCT: Memory-Centric X-ray CT Reconstruction with Massive Parallelization” . MemXCT 's single-device performance, parallelized via OpenMP and MPI, was characterized using AMD Zen2 CPU cores and NVIDIA V100 GPU devices running on the Microsoft Azure cloud. We were able to reproduce most of the results, and exceed the performance of larger inputs, on an AMD EPYC HBv2 cluster. We were also able to reproduce the strong scaling trends for optimized CPU and GPU versions. Slight variations in performance of the CPU version were observed due to differences in the underlying hardware, input size, and number of available nodes. Digital artifacts from these experiments are available at: 10.5281/zenodo.5598108