Portrait of Koorosh Roohi

Koorosh Roohi

Machine learning, computer vision, and multi-modal sensing.

Ph.D. candidate, University of Toronto Biomedical Engineering (doctoral program); B.Sc. in Computer Engineering, Amirkabir University of Technology.

koorosh.roohi@mail.utoronto.ca

Curriculum vitæ (PDF)

Research Interests

Ph.D. candidate at the University of Toronto, advised by Prof. Atena Roshan Fekr and Prof. Alex Mihailidis. I am most interested in work that sits where scientific inquiry meets engineering judgment—taking advances from machine learning and sensing research and shaping them into methods that can be measured, deployed, and used without leaving their assumptions at the lab door.

  • Deep learning for multi-modal sensing and 3D point cloud processing (mmWave radar, RGB-D, IMU, BLE)
  • Human activity and sequence recognition; spatio-temporal models in clinical and ambient environments
  • Indoor localization, sensor fusion, and real-time inference on edge and wireless pipelines
  • Generative models: diffusion and image synthesis; video-to-video translation and style transfer
  • Vision–language models, multi-agent systems, and learning under limited labeled data
  • Machine learning for infection transmission and exposure risk in healthcare settings

News

Recent papers and presentations. Full list on Google Scholar.

  • Paper published: Deep learning-based recognition of simulated nursing activities for infection risk assessment (with Atena Roshan Fekr), Machine Learning: Health. paper

  • Survey published: A comparative analysis of indoor localization technologies: a review of the literature (with Atena Roshan Fekr), Computer Networks. paper

  • Oral presentation at IEEE EMBC: Using mmWave radar and deep learning to classify caregiver activities for infection prevention (with Atena Roshan Fekr). proceedings

  • Paper published: FUVT: a deep few-shot unsupervised learning-based video-to-video translation scheme using Kalman filtering and relativistic GAN (with Alireza Esmaeilzehi and M. Omair Ahmad), Signal, Image and Video Processing. paper

  • Manuscript submitted (under review at Smart Health): Real-time caregiver activity recognition with potential for infection prevention in hospitals (with Atena Roshan Fekr).

  • EPIC Doctoral Award ($10,000 CAD), Emerging and Pandemic Infections Consortium.

Experience

  • 2023 — present

    AI Manager · Masterly Inc., Toronto

    AI products for organizations; cloud deployment on AWS.

    • Led end-to-end development of Masterly Forms, a collaborative platform with AI-assisted form design and completion.
    • Built Masterly Earendel, a vision–language-model-based video analysis pipeline for event detection and alerting in an agentic architecture.
    • Leading development of Masterly FinSuite, an LLM-driven financial portal for reporting automation and decision support.
    • Production infrastructure on AWS (SageMaker, Bedrock, Lambda, EC2); supervised a team of five developers and shipped modules in PyTorch and .NET.
  • 2022

    Computer vision engineer (part-time) · Crouse Company, R&D, Tehran

    Quality inspection for automotive displays.

    • OpenCV-based defect-detection pipeline; Isolation Forest and Tesseract OCR for pixel-level anomaly screening.
  • 2019 — 2022

    Client developer (part-time) · Quiz of Kings Studio, Tehran

    Unity client for a large-scale mobile title.

    • Client-side feature work and migration of legacy code from Corona to Unity.

Background — briefly

Education

Ph.D. candidate in Biomedical Engineering, University of Toronto (2023 onward; expected completion 2028). Dissertation area: learning and multi-modal sensing in clinical settings, including 3D data, sequential modeling, and system integration. B.Sc. in Computer Engineering, Amirkabir University of Technology (Tehran Polytechnic), 2023.

Teaching & community

Tutorial teaching assistant, Department of Computer Science, University of Toronto: System Programming (2025, 2026), Microprocessor Systems (2024), Software Design (2023, 2024, 2025). Previously head teaching assistant at Amirkabir in artificial intelligence, programming languages, algorithms, and related courses. Peer reviewer for Circuits, Systems, and Signal Processing. EPIC Doctoral Award, Emerging and Pandemic Infections Consortium (2025).