Menu

Copyright © All rights reserved | This template is made with by Colorlib

Research Experience

  • Visual analytics for content moderation

    May 2021 - Present

    Data driven decision making has been on trend lately, but the issue surrounding the dissemination of misinformation has been a constant topic of discussion for the researchers. The goal of this work is to utilize visual analytics to detect signals of misinformation from social media platforms such as Twitter. This project facilitates the human-technology partnership by designing new technologies to augment moderator performance.

  • Visualization based Communication

    Sep 2019 - Present

    This work focuses on the area of communicative visualizations to characterize the cognitive effort required for decoding scientific charts. With this work we aim to develop a systematic understanding of visualizations to bridge the link between visual representation of the data and the information perceived by the users. Our work revolves around the idea of devising reasoning strategies that in uence the design and interpretation of scientific visualizations. We leverage techniques from Natural Language Processing to characterize the interaction between textual and graphical elements of the visualization. In this project, we calibrate the decoding effort and analyze design choices for scientific communication.

    • Fairness in Data Driven Decision Making

    May 2020 - May 2021

    Data driven decision making has been on trend lately, but the issue surrounding the potential discrimination has been a constant topic of discussion for the researchers. Using this work, we aim to facilitate fair decision making by studying the trade-offs between fairness and accuracy using education related open datasets through visualizations.

  • Malware Detection using Deep Learning

    Nov 2018 - May 2019

    In this work, we have explored a new technique to represent malware as images. We then used existing neural network techniques, for classifying images, to train a classifier for classifying new malware files into their respective classes. By converting the file into an image representation we have made our analysis process independent of any tool also the process becomes less time consuming. With our model we have been able to get an accuracy of 98.21 % in classifying malware samples

Education

  • New Jersey Institute of Technology

    August 2019 - Present

    Third year Doctoral student (advisor : Dr Aritra Dasgupta), Department of Informatics, Ying Wu College of Computing, Newark, New Jersey

  • Gujarat Technological University

    August 2015 - June 2019

    Bachelor's of Engineering, Department of Computer Engineering Atmiya Institute of Technology and Science,Rajkot,Gujarat,India

Achievements

  1. The final year undergraduate project was awarded as Best Innovative Engineering Award by Indian Society for Technical Education(ISTE) in October 2019.

  2. Awarded Shri Dewang Mehta IT award thrice in September 2019,August 2018,September 2017 for excellence in Bachelor's of Engineering.

  3. Final year undergraduate project-"Malware Detection using Deep Learning" was funded by Student Startup and Innovation Policy(SSIP)-an initiative by Government of Gujarat to promote young inno- vators.

  4. Project-"Malware Detection using Deep Learning" won gold medal at State level Indian Science & Engineering Fair (INSEF) Level - 2 on 5th January, 2019 in collaboration with Science Society of India, Banglore, India.