Community & Impact

Workshops, competitions, talks, and milestones from my journey in AI and Data Science.

Early Achievement: Computer Vision for Intelligent Traffic Monitoring
AICommunity

Early Achievement: Computer Vision for Intelligent Traffic Monitoring

Developed a computer vision pipeline for the Omdena Bangladesh Chapter challenge using YOLOv4 for multi-class vehicle detection and DeepSORT for object tracking. The system detects 9 vehicle classes and visualizes relative vehicle velocity in real time (green for positive, red for negative motion). Despite limited time and an imbalanced dataset, the project demonstrated a strong proof of concept with scope for improved accuracy through future data collection and model refinement.

Judge at DL Sprint 4.0, BUET CSE Fest — image 1
Judge at DL Sprint 4.0, BUET CSE Fest — image 2
Judge at DL Sprint 4.0, BUET CSE Fest — image 3
CompetitionCommunity

Judge at DL Sprint 4.0, BUET CSE Fest

Served as a judge for DL Sprint 4.0, a Kaggle competition held during BUET CSE Fest, evaluating solutions for Bengali long-form speech recognition and speaker diarization. It was rewarding to return to my alma mater and see participants tackle challenging problems with innovative modeling techniques, system designs, and even newly created datasets for Bengali speaker diarization. Having also judged previous DL Sprint competitions as part of Bengali.AI, it was great to continue supporting the growth of Bangladesh's AI research community.

Delivering Generative AI Training at Robi Axiata — image 1
Delivering Generative AI Training at Robi Axiata — image 2
SpeakingAI

Delivering Generative AI Training at Robi Axiata

Conducted two Generative AI training sessions for the Strategic Planning & EPM team at Robi Axiata, covering Large Language Models (LLMs), prompt engineering, AI reasoning, hallucinations, and practical AI applications in business. The session focused on helping participants understand how to effectively leverage AI tools for productivity, research, strategic decision-making, and responsible AI adoption as part of Robi's AI-native transformation.