Research

Research Interests

My research uses fundamental ideas from machine learning and computational science to study crowds in videos and online communities. I develop theoretical and applied models and algorithms to examine the formation of groups and the emergent properties that arise from crowd behaviour in the often inter-related fields of:

  • Computer Vision/Multimedia: physics-based methods for group analysis in video
  • Social Computing: group collaboration and virtual communities, especially for science learning
  • Data Science: scientific workflows for multimedia analysis and reproducibility

Research Projects

My research projects tend to be inter-disciplinary in nature. I conduct research in machine learning, computer vision, social computing, and cyberlearning. I rely upon fundamental ideas from theoretical computational science to address significant research problems in these areas.

Some of these projects are:

  1. Computer Vision/Multimedia
    1. Multimedia Integration via Data-Driven Hamiltonian Monte Carlo (DDHMC)
    2. Group Detection and Analysis in Video
    3. Human Action Image/Hamiltonian Energy Signatures for Video Activity Recognition
  2. Social Computing for Science Learning
    1. Collaborative Argumentation
    2. Threaded Discussion Metrics and Analysis
    3. Question & Answer Online Communities
  3. Data Science
    1. Multimedia Analysis for Human Trafficking Detection
    2. Machine Learning Methods for Data Analysis using Semantic Workflows
    3. Reproducibility via Semantic Workflows


Profile

Ricky J. Sethi

Ricky J. Sethi is currently an Assistant Professor of Computer Science at Fitchburg State University, Director of Research for The Madsci Network, and Team Lead for SNHU Online.

  • Affiliations:
    • Fitchburg State University
    • The Madsci Network
    • Southern New Hampshire University
  • Education:
    • University of California, Berkeley
    • University of Southern California
    • University of California, Riverside
  • Field of Research:
    • Computer Vision/Multimedia
      Group analysis in video using physics-based, machine learning models
    • Social Computing
      Virtual communities & group collaboration for science learning
    • Data Science
      Multimedia analysis and reproducibility via semantic workflows