Bridging the gap between cutting-edge research and real-world impact
For a summary of links to various online profiles, you can check out my linktree.
I'm a multidisciplinary computational scientist and software engineer at the intersection of Computer Vision, Machine Learning and Bioscience Engineering, with 10 years of combined experience across academia, industry, and R&D environments.
10 years of experience across 4 research and industry environments
🧠 AI in Neurophysiology → 🚀 Industry AI → 🐞 Agricultural AI → 🛰️ AI for Earth Observation
Lab Research Applied Solutions Field Applications Global Monitoring
Timeline:
2015-2017: Neurophysiology (KUL) → 2017-2018: ML-team (Faktion) → 2018-2024: MeBioS (KUL) → 2024-Present: Remote-Sensing (VITO)
I'm developing AI models for the Land Cover and Forest Monitoring (LCFM) project at Vito, part of the EU's Copernicus programme, in the team that released the famous ESA WorldCover products. My work involves building multi-stage AI pipelines that process satellite data to create global land cover maps at unprecedented 10m resolution—a tenfold improvement over previous products. I specialize in training cloud segmentation models for quality signal identification, maintaining our code repositories on github (soon to be open-sourced), and deploying classification models that generate annual land cover maps for the entire planet, directly supporting EU environmental policy and climate monitoring initiatives.
🛰️ Satellite Data → ☁️ AI Cloud Detection → 📊 Quality Composites → 🗺️ Global Land Cover Maps
10m Resolution • Annual Updates • Planetary Scale
Keywords: Web Development, CLI Tools, DevOps, Computer Vision, Image Processing, IoT, Python, Flask, NiceGUI, Solara, Streamlit
desto - Web dashboard and CLI for managing scripts in tmux sessions
- Full-stack web application with real-time system monitoring, live log viewing, script scheduling, and both web interface and command-line functionality.
- Built with modern web technologies and Docker deployment, showcasing full-stack development skills beyond core AI/ML expertise.
plakakia - Python image tiling library for computer vision tasks
- High-performance image tiling tool for object detection and segmentation datasets, utilizing multiprocessing and numpy for efficient processing.
- Features online/offline processing modes, bounding box handling, duplicate removal, and a Streamlit demo interface.
- Benchmarked on multiple public datasets with comprehensive performance metrics and extensive documentation.
Home_Surveillance_with_Python - Motion detection surveillance system
- Complete IoT surveillance solution using OpenCV for motion detection, Flask for web streaming, and Pushbullet API for mobile alerts.
- Raspberry Pi compatible with picamera support, demonstrating practical IoT deployment and computer vision integration.
- Features real-time video streaming, automated alerting, and image capture with motion region highlighting.
🛰️ Remote Sensing & AI at VITO (Current; 2024-)
- Develop reliable earth land cover classification systems through LCFM project
- Apply hyperspectral satellite data analysis and ML models for environmental datasets
- Work with cloud services, Hadoop, Spark, and AWS for large-scale processing
- Contributing to EU Commission projects for sustainable development and climate change mitigation.
🐞 PhD & Postdoc in Bioscience Engineering at KU Leuven (4 + 1.5 years; 2018-2022 + 2022-2024)
PhD Focus: Optical Insect Identification using AI
Postdoc: Led AI projects, mentored PhD researchers, specialized in hyperspectral imaging
- Built comprehensive AI systems for insect recognition using computer vision and audio analysis (see insect-trap, wbai, stickybugs-ai)
- Developed software tools for IoT devices, desktop systems, and cloud infrastructure (see photobox, example publication)
- Deployed production API server on AWS serving AI models and tools to external companies via a web interface (demo-setup, demo-interface, demo-label-tool)
5 publications in high-impact journals | Created plakakia library
🚀 Data Scientist at Faktion (1 year; 2017-2018)
Applied AI solutions for industry clients including predictive maintenance (Bridgestone), sales analytics (Aliaxis), and computer vision POCs.
Achievement: 🏆 Won hackathon on Activity Recognition (Vinci Energies)
🧠 Deep Learning Research at KU Leuven (2 years; 2015-2017)
Studied deep CNNs and their resemblance to biological visual systems. Developed models to predict neuronal activity from artificial neuron activations.
4 publications in top neuroscience journals | Presented at VSS conference (Florida, USA)
🐞 PhD in Bioscience Engineering (KU Leuven, Belgium 🇧🇪; 4 years; 2018-2022)
Successfully completed doctoral research with a focus on optical insect identification using signal processing and computer vision with AI/ML/DL
🧠 PhD Research* - Neurophysiology Lab (KU Leuven, Belgium 🇧🇪; 2 years; 2015-2017)
*Fulfilled requirements early, but exited programme
Explored computational neuroscience applications and deep learning models for biological neurons
🎓 MSc. Machine Learning (KTH Royal Institute of Technology, Stockholm, Sweden 🇸🇪; 2015)
Specialized in Computational Neuroscience and Spiking Neural Networks
Thesis research simulating neocortical structures using NEST simulator in Python
🎓 BSc. Computer Science (Aristotle University of Thessaloniki, Greece 🇬🇷; 2013)
Built a solid foundation in computing theory and educational information systems
AI/ML: Computer Vision • Deep Learning • CNNs • YOLO • Time-Series Analysis
Cloud: AWS • Docker • FastAPI • Web GUIs (Streamlit, Solara, NiceGUI...)
Data: Hyperspectral Imaging • Satellite Data • IoT Sensors • Big Data Processing
∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿∿
🌱 I'm always interested to learn about how Artificial Intelligence can improve our lives.
💬 To reach out, send an email at kalfasyan[at]gmail[dot]com
🔗 Check my linktr.ee
📚 Researcher profiles:
🧬 orcid
🔬 scholar
📖 researchgate
🌐 Stay connected through the following social media channels: bluesky, linkedin, github