معرفی
Hamid Sarmadi serves as an Associate Senior Lecturer at Halmstad University's School of Information Technology, where his work bridges theoretical AI research with practical industrial applications. His research portfolio demonstrates significant contributions to computer vision systems for geospatial analysis and transportation efficiency, while actively teaching Python programming courses to undergraduate students.
His academic journey includes:
- Bachelor of Computer Science, Tehran University (Iran)
- Master of Machine Learning, KTH Royal Institute of Technology (Sweden)
- PhD in Computer Vision, University of Cordoba (Spain)
Sarmadi's research centers on three interconnected domains: satellite-based poverty mapping using convolutional neural networks, predictive maintenance systems for urban transportation infrastructure, and driver behavior analysis through attention modeling. His innovative approach integrates physics-based constraints with data-driven methodologies, particularly evident in air leak detection systems for city buses where he fuses engineering principles with machine learning. This cross-disciplinary methodology addresses real-world challenges in sustainable development and transportation efficiency while maintaining technical rigor in model explainability and bias mitigation.
Analysis of his 2022-2024 publications reveals a clear trajectory toward socially impactful AI applications. His satellite poverty mapping work examines human-AI collaboration dynamics, while transportation research focuses on sustainability metrics like fuel consumption optimization. The consistent thread across these domains is the development of interpretable AI systems that incorporate domain-specific knowledge, moving beyond pure black-box approaches to create solutions with verifiable real-world utility.
As course responsible for Python programming instruction, Sarmadi contributes directly to technical education at Halmstad University. While student advising details aren't specified in available records, his research output suggests active supervision of graduate projects in computer vision and machine learning applications. His work demonstrates strong potential for future expansion into explainable AI frameworks for public infrastructure management and climate-resilient transportation systems.
