Machine learning for healthy lifestyle habits
Maintaining awareness of dietary habits is important for health, but traditional methods, such as manual food journaling, are time-consuming and often inaccurate. Advances in computer vision offer opportunities to automate this process, making camera-based dietary assessment more convenient and reliable.
I am currently developing different tools based on machine learning (ML) connected to healthy lifestyles, including dietary habits. We work on tools that can be used to efficiently track what, how much, and when you eat and analyze the long-term patterns to provide valuable feedback. And a tool that teach you how to change lifestyle habits into more healthy options using engaging quiz method. And a tool that takes an online recipe and modifies it into a more healthy option.
You can try some of the software that I and my students have developed here:
- HealthyMindset - pure question-based learning for healthy dietary habits.
- Healthy Recipe Modifier - Takes your popular recipe and makes it healthier
Our you can read more about these projects here:
- Esaias Bevegård and Eugén Bevegård, Automated Dietary Analysis Using Computer Vision and Large Language Models: An iOS Prototype, BSc Thesis, KTH, 2025.
- Jonas Stylbäck, A Step Towards a Multi-Stage, Visual-Based Dietary Assessment Smartphone Application: A Computational Approach to Food Volume Estimation Using Smartphone-Based Augmented Reality, MSc Thesis, KTH, 2025.
- Simon Fridh, Optimering av matlagningsrecept baserat på näringsinnehåll och likhet, genom artificiell intelligens: Utveckling och utvärdering av en prototypapplikation, BSc Thesis, KTH, 2026.
- Martin Jacobsson, Mert Affan, Sharannya D/o Ramesh, Katrine Risto, Hao Tang, Natalia Tutnjevic, AI-Based Pure Question-Based Learning for Lifestyle Interventions, Poster at Medicinteknikdagarna, Örebro, October 13-15, 2026
