Human-Centered AI · Physiological ML · Adaptive Learning

Building AI systems that understand human learning, effort, and context.

I’m Arkaan, an AI Product Manager, Independent AI Researcher, and ML Engineer. My current research direction focuses on physiological and behavioural machine learning for cognitive load, stress-aware systems, and adaptive learning.

I have experience building AI and software systems across enterprise architecture, legal technology, computer vision, biometrics, and drone-based analytics. I am preparing a long-term research path toward doctoral study in human-centred AI and physiological machine learning.

🧠 Cognitive Load   ·   📈 Adaptive Learning   ·   ⌚ Wearable Signals   ·   🤝 Human-Centered AI

AI

Product

ML

Research

PhD

Track

Research Pipeline

My research direction connects human signals, lightweight modelling, adaptive recommendations, and practical learning support.

🧑‍💻

Learning Session

Tasks, study goals, difficulty, confidence, and performance.

Human Signals

Self-reported load, fatigue, sleep, HRV, heart rate, and behavioural patterns.

📊

Load Modeling

Lightweight rules, interpretable metrics, and future physiological ML models.

🎯

Adaptive Support

Study pacing, review strategy, recovery, and personalised recommendations.

Selected Work

🧩

AI Product and System Strategy

I currently work in product management, focusing on user needs, technical feasibility, product strategy, and system execution.

🏛️

Enterprise AI and Architecture

Previously, I worked on enterprise-scale systems, AI feasibility, automation, document intelligence, and system architecture.

👁️

Computer Vision and Applied ML

My earlier work involved computer vision, biometrics, OCR, legal-tech automation, drone analytics, and image quality assessment.

Current Direction

My long-term goal is to pursue doctoral research in human-centred AI, with a focus on physiological and behavioural machine learning for cognitive load, stress, and adaptive learning. I am particularly interested in research that bridges rigorous machine learning evaluation with practical systems that people can actually use.