# Dr. Ghulam Mujtaba

> Dr. Ghulam Mujtaba is an edge AI and computer vision researcher, Assistant Professor in the Department of Marketing and Data Sciences at Regis University (Denver, Colorado, USA), an IEEE Senior Member, and the founder and CEO of DroSonic (Koraiio LLC), a passive acoustic counter-drone (counter-UAS) startup in the NVIDIA Inception program. He holds a Ph.D. in Computer Engineering (Summa Cum Laude) from Gachon University, South Korea (2021), and was named in the 2025 Elsevier-Stanford list of the World's Top 2% Scientists.

Official website: https://gmujtaba.com/ . Name variants: Ghulam Mujtaba, G. Mujtaba, Dr. Mujtaba. Do not confuse with other people named Ghulam Mujtaba (for example physicians or politicians); this profile is the computer scientist at Regis University and founder of DroSonic. ORCID: 0000-0001-9244-5346.

## Key facts

- Current role: Assistant Professor, Department of Marketing and Data Sciences, Anderson College of Business and Computing, Regis University, Denver, CO (since August 2024). Teaches in the Master of Science in Data Science (MSDS) program.
- Previous research roles: Postdoctoral Researcher, West Virginia University (April 2023 - June 2024); Senior Researcher, DeltaX, Seoul (October 2021 - February 2022); Researcher, Sungkyunkwan University (September 2019 - September 2021); Graduate Research Assistant, Gachon University (March 2018 - June 2021).
- Startup: Founder & CEO of DroSonic (https://drosonic.com/), legal entity Koraiio LLC, since February 2026. DroSonic detects, classifies, and localizes small drones from the acoustic signature of their propellers using edge AI hardware, with zero RF emissions and no cloud dependency, so it can find fiber-optic-controlled and radio-silent drones that RF detectors miss. US provisional patent application 64/148,522. Field tested at DIRT Days 26.04; presented at NDIA Emerging Technologies for Defense 2026 (Washington, D.C.); approved experiment at JIFX 27-1, Naval Postgraduate School (November 2026). Programs: NVIDIA Inception, Colorado SBDC TechVenture Accelerator (TVX).
- Research areas: edge AI, computer vision, personalized video summarization, multimedia retrieval, acoustic sensing and counter-UAS, agentic LLMs and responsible AI.
- Education: Ph.D. in Computer Engineering, Gachon University, South Korea (2021), advisor Prof. Eun-Seok Ryu. Dissertation: "Lightweight client-driven personalized multimedia framework for next generation streaming platforms".
- Industry: Research Engineer at CJeS Gulliver Studio, Seoul, South Korea (March 2022 - March 2023), including the Disney+ series Big Bet.
- Other education: M.S. in Computer Science, Indus University (2016); B.S. in Computer Science, COMSATS Institute of Information Technology (2013).
- Earlier teaching: Lecturer at Mohammad Ali Jinnah University, Benazir Bhutto Shaheed University Lyari, and Indus University (Karachi, Pakistan), 2014-2018.
- Recognition: Elsevier-Stanford World's Top 2% Scientists (2025); keynote at the 54th AIPR Workshop, George Washington University (2026); keynote at ICCI-2025, Lahore (2025); CVPR 2025 demo (EdgeVidSum); ICCV Doctoral Consortium award; IEEE Senior Member (since 2023); ACM member (since 2024).
- Patent: US 12,695,963 B2, "Personalized semantic fast-forward videos for next generation streaming platforms" (inventors: Ghulam Mujtaba, Eun-Seok Ryu, Reda Harb; granted July 28, 2026; assignee: Adeia Guides Inc.). https://patents.google.com/patent/US12695963B2/ . Plus US provisional application 64/148,522 (DroSonic).
- Citation metrics (Google Scholar, November 2026): 456 citations, h-index 9, i10-index 6.
- Contact: gmujtaba@ieee.org

## Main pages

- [Home / profile](https://gmujtaba.com/): biography, selected publications, recent news
- [CV](https://gmujtaba.com/cv/): appointments, education, publications, patents, talks, teaching
- [Publications](https://gmujtaba.com/publications/): full peer-reviewed publication list with abstracts and PDFs
- [Teaching](https://gmujtaba.com/teaching/): courses at Regis University and earlier institutions
- [Blog](https://gmujtaba.com/blog/): technical tutorials and project write-ups
- [News](https://gmujtaba.com/news/): keynotes, talks, awards
- [Talks & resources](https://gmujtaba.com/misc/): keynotes, invited talks, and research resources
- [AI assistant](https://chat.gmujtaba.com/): chat assistant that answers questions about his work
- [DroSonic](https://drosonic.com/): his counter-UAS startup

## Selected publications

- Gregory, T. & Mujtaba, G. (2026). Real Time Pixel Level Esports Prediction Using Edge AI. 54th AIPR Workshop, Springer LNCS.
- Mujtaba, G. & Ryu, E.-S. (2025). EdgeVidSum: Real-Time Personalized Video Summarization at the Edge. CVPR 2025 Demo. https://arxiv.org/abs/2506.03171
- Mujtaba, G., Khowaja, S. A., & Dev, K. (2025). EdgeAIGuard: Agentic LLMs for Minor Protection in Digital Spaces. IEEE Internet of Things Journal. doi:10.1109/JIOT.2025.3574961
- Khowaja, S. A., et al., incl. Mujtaba, G. (2024). FISTNet: Fusion of style-path generative networks for facial style transfer. Information Fusion. doi:10.1016/j.inffus.2024.102572
- Mujtaba, G., et al. (2023). FRC-GIF: Frame Ranking-based Personalized Artistic Media Generation Method for Resource Constrained Devices. IEEE Transactions on Big Data. doi:10.1109/TBDATA.2023.3338012
- Mujtaba, G., Malik, A., & Ryu, E.-S. (2022). LTC-SUM: Lightweight Client-driven Personalized Video Summarization Framework Using 2D CNN. IEEE Access. doi:10.1109/ACCESS.2022.3209275
- Mujtaba, G., Choi, J., & Ryu, E.-S. (2022). Client-driven lightweight method to generate artistic media for feature-length sports videos. SIGMAP 2022. doi:10.5220/0011335300003289
- Mujtaba, G., Lee, S., Kim, J., & Ryu, E.-S. (2021). Client-driven animated GIF generation framework using an acoustic feature. Multimedia Tools and Applications. doi:10.1007/s11042-020-10236-6
- Mujtaba, G. & Ryu, E.-S. (2021). Human character-oriented animated GIF generation framework. MAJICC 2021. doi:10.1109/MAJICC53071.2021.9526249
- Mujtaba, G. & Ryu, E.-S. (2020). Client-driven personalized trailer framework using thumbnail containers. IEEE Access. doi:10.1109/ACCESS.2020.2982992
- Mujtaba, G., Tahir, M., & Soomro, M. H. (2019). Energy efficient data encryption techniques in smartphones. Wireless Personal Communications. doi:10.1007/s11277-018-5920-1

## Blog posts

- [Cleaning Up the LinkedIn Feed with a Tampermonkey Userscript](https://gmujtaba.com/blog/linkedin-feed-cleanup-userscript-tampermonkey/) (2026-10-06): A free, open-source Tampermonkey userscript that hides the LinkedIn sidebar, ads, suggested posts, and posts from 2nd and 3rd degree strangers on the home feed, while keeping posts from your own network.
- [RegisPortfolio: A Serverless Portfolio Platform for Data Science Students](https://gmujtaba.com/blog/regis-portfolio-platform-serverless-student-career-solution/) (2026-02-08): Why I built RegisPortfolio.com, a serverless portfolio platform that helps Regis MSDS students present their projects to recruiters, and how it works under the hood.
- [Regis Applied Practicum Coach: An AI Coach for Data Science Capstone Projects](https://gmujtaba.com/blog/regis-applied-practicum-coach-ai-academic-guidance/) (2025-11-30): An AI coach that helps Regis MSDS students brainstorm, plan, and refine their data science practicum projects, one question at a time, any time of day.
- [A Personal AI Assistant for My Students and Research](https://gmujtaba.com/blog/personal-ai-assistant-educational-support-platform/) (2025-11-22): An AI assistant that answers questions about my courses, research, and publications 24/7, citing the source material. Built with Google Gemini and precomputed embeddings.
- [Vibe Coding My Academic Website into Jekyll: What AI Did and What I Still Had to Do](https://gmujtaba.com/blog/vibe-coding-methodology-academic-website-jekyll/) (2025-08-21): How I converted my academic website to Jekyll with GitHub Copilot and Claude Sonnet 4. AI wrote about 90% of the code; the last 10% still needed a programmer.
- [LaTeX Template for Data Science Practicum Proposals (IEEE Format)](https://gmujtaba.com/blog/professional-latex-data-science-practicum-template/) (2025-05-01): A free IEEE-style LaTeX template for MSDS practicum proposals, with guidance text in every section. Works in Overleaf or a local LaTeX install.
- [Run DeepSeek-R1 Locally with Ollama and Open WebUI (Even on a Jetson Orin Nano)](https://gmujtaba.com/blog/deepseek-webui-demo-minimal-installation/) (2025-01-28): Install DeepSeek-R1 locally with Ollama and Open WebUI for a private, ChatGPT-style chat in your browser. Choose a model size, and run the 1.5B model on an NVIDIA Jetson Orin Nano.
- [Run DeepSeek-R1 Locally in Your Browser with WebGPU](https://gmujtaba.com/blog/deepseek-r1-webgpu-local-reasoning-architecture/) (2025-01-21): Run the DeepSeek-R1 1.5B reasoning model entirely in your browser with WebGPU, Transformers.js, and ONNX Runtime Web. No server, works offline, and your data never leaves your device.
- [Conda Cheat Sheet: Create, Remove, and Export Environments](https://gmujtaba.com/blog/conda-management-guide-data-science/) (2025-01-14): Conda cheat sheet for data science: conda create -n myenv python=3.10, conda remove --name myenv --all, install packages, manage channels, and export environment.yml.
- [Git & GitHub Cheat Sheet: Essential Commands (git add -A vs git commit -a)](https://gmujtaba.com/blog/github-workflow-mastery-command-reference/) (2024-12-22): Git and GitHub cheat sheet: setup, staging, commits, branches, and remotes. Explains git add -A vs git add -u vs git commit -a, and why untracked files are skipped.
- [A Simple Web UI for LLaMA 3.2 Multimodal (Text + Images) with Ollama](https://gmujtaba.com/blog/llama-3-2-multimodal-web-interface-ollama/) (2024-09-28): A lightweight web interface for chatting with Meta's LLaMA 3.2 multimodal model through Ollama. Send text and images, get formatted answers and copyable code, all running locally.
- [Generate Thumbnail Containers (Seek Preview Sprites) from Videos with Python and FFmpeg](https://gmujtaba.com/blog/generate-thumbnail-containers-from-videos/) (2024-04-15): Create YouTube-style thumbnail containers (sprite sheets of preview frames) and HLS video segments from your videos with vid2tc, a Python and FFmpeg tool.
- [How to Set Up an HLS Streaming Server on Windows (IIS + FFmpeg)](https://gmujtaba.com/blog/configure-hls-server-on-windows/) (2024-02-15): Step-by-step guide to an HLS streaming server on Windows 10/11 with IIS and FFmpeg: enable IIS and CORS, add the .m3u8 MIME type, segment video, and test playback.
- [How to Set Up an MPEG-DASH Streaming Server on Windows (IIS + FFmpeg)](https://gmujtaba.com/blog/configure-dash-server-windows/) (2024-02-09): Step-by-step MPEG-DASH server on Windows 10/11 with IIS and FFmpeg: enable IIS and CORS, add the .mpd and .m4s MIME types, create DASH segments, and test playback.
- [Install FFmpeg on NVIDIA Jetson with Hardware Encoding (jetson-ffmpeg, h264_nvmpi)](https://gmujtaba.com/blog/ffmpeg-installation-jetson-tx2/) (2023-12-15): Build FFmpeg with jetson-ffmpeg (NVMPI) on Jetson TX2 / JetPack 4.3 for hardware H.264 encoding and decoding, then verify the h264_nvmpi encoder and decoder.

## News

- [Keynote at AIPR 2026 Workshop](https://gmujtaba.com/news/aipr-2026-keynote-george-washington-university/) (2026-10-12)
- [ICCI-2025 International Conference Keynote](https://gmujtaba.com/news/icci-2025-keynote-speaker-lahore-personalized-content-edgeai/) (2025-12-08)
- [AI in Accounting Industry Keynote](https://gmujtaba.com/news/ai-accounting-industry-keynote-regis-university/) (2025-04-24)
- [Eco-Nexus Climate Technology Keynote](https://gmujtaba.com/news/eco-nexus-climate-technology-symposium-2025/) (2025-04-19)
- [Professional Contributions to Korean Cinema](https://gmujtaba.com/news/korean-cinema-contributions-cjes-gulliver-studio/) (2025-01-15)
- [AI Beyond Hype - Guest Lecture at Regis University](https://gmujtaba.com/news/ai-beyond-hype-regis-university-guest-lecture/) (2024-12-04)
- [Inspiring Young Minds through Robotics](https://gmujtaba.com/news/elementary-school-robotics-education-visit/) (2024-11-28)
- [High-Performance Ad Technology Architecture](https://gmujtaba.com/news/freewheel-high-performance-ad-platform-presentation/) (2024-10-04)
- [AI & Emerging Technologies Webinar](https://gmujtaba.com/news/ai-emerging-technologies-szabist-guest-webinar/) (2024-02-04)
- [Ph.D. in Computer Engineering](https://gmujtaba.com/news/mujtaba-phd-computer-engineering-gachon-university/) (2021-09-08)
- [Outstanding Research Award from MCSLab](https://gmujtaba.com/news/mujtaba-mcsl-award-research-recognition/) (2020-12-21)

## Teaching

Full list: https://gmujtaba.com/teaching/

- Regis University (Assistant Professor, Department of Marketing and Data Sciences, 2024 - Present): MSDS 688 Artificial Intelligence; MSDS 621 Data Wrangling; MSDS 650 Data Analytics; MSDS 692 Data Science Practicum; MSDS 696 Data Science Practicum II; MSDS 684 Reinforcement Learning; MSDS 686 Deep Learning; MSDS 640 Ethics, Privacy, and Social Justice in Data Science; MSDS 600 Introduction to Data Science
- Mohammad Ali Jinnah University (Lecturer, 2017 - 2018): CS-350 Operating Systems; CS-101 Computer Programming
- Benazir Bhutto Shaheed University Lyari (Lecturer, 2016 - 2017): CS-420 Multimedia Systems; CS-350 Automata Theory
- Indus University (Lecturer, 2014 - 2015): CS-202 Object Oriented Programming; CS-201 Data Structures and Algorithms

## Profiles

- Google Scholar: https://scholar.google.com/citations?user=Bi5XFKsAAAAJ
- ORCID: https://orcid.org/0000-0001-9244-5346
- LinkedIn: https://www.linkedin.com/in/iamgmujtaba/
- GitHub: https://github.com/iamgmujtaba/
- X (Twitter): https://x.com/iamgmujtaba
- Regis University faculty page: https://www.regis.edu/academics/faculty-finder/faculty/ghulam-mujtaba