An intelligent, ontology-based system that recommends personalized recipes based on user health profiles using OWL 2.0, Protégé, and DL Queries.
This project is part of my MSc in Computer Science & Technology at Ulster University, UK. It focuses on applying Knowledge Representation and Reasoning (KRR) to solve a real-world challenge: providing smart, health-focused recipe recommendations.
Rather than using a simple filtering system, this project leverages ontologies, semantic relationships, and DL Queries to infer suitable recipes for users with conditions like diabetes, dietary restrictions (e.g., vegan, gluten-free), or seasonal preferences.
- 📊 Personalized Recipe Reasoning using Description Logic (DL) queries
- 🧩 Ontology built in Protégé using OWL 2.0
- 🍎 Semantic links between:
- Recipes
- Ingredients & Nutrients
- Dietary Restrictions
- Cooking Methods
- Meal Types & Cuisines
- ⚖️ Logical constructs:
equivalence,restrictions,transitiveandsymmetricproperties
Here’s a breakdown of the key tools, frameworks, and technologies used in this project:
| Category | Tools & Technologies |
|---|---|
| 🧠 Ontology Modeling | |
| 📘 Language Format | |
| 🔍 Reasoning Engine | 🧠 DL Queries (Description Logic), 📐 Prolog (explored for rule-based logic) |
| 📑 Documentation | 📝 Markdown, 📄 PDF (Research Paper) |
| 🔧 Version Control |
This ontology-based system can be applied across multiple domains that require intelligent, personalized food and health recommendations:
Suggest personalized recipes based on health conditions (e.g., diabetes, heart disease), dietary preferences, or nutrient goals.
Help dietitians and healthcare providers recommend suitable meals for patients with specific medical or nutritional needs.
Integrate into chatbots to answer questions like “What can I eat with high blood pressure?” or “Suggest a vegan, high-protein dinner.”
Enable mobile health apps to go beyond filters by using semantic reasoning to tailor recommendations intelligently.
Restaurants can offer curated menus for customers with allergies, food intolerances, or lifestyle preferences (e.g., keto, vegan, gluten-free).
Power intelligent agents that reason over food, health, and diet-related knowledge using ontologies and DL logic instead of flat databases.
healthy-recipe-ontology/
├── README.md
├── ontology/
│ ├── Healthy_Recipe_Recommender_Updated.owl # (Protégé/OWL)
│ └── DLQueries.txt # List of DL queries for reasoning
├── docs/
│ └── Healthy_Recipe_Recommender_Ontology_Report.pdf # Full academic paper
└── Healthy_Recipe_Recommender_Ontology_Report.docx
├── screenshots/ # Protégé hierarchy or query view
│ └── 2.png
└── 3.png
└── 4.png
└── 5.png
└── 6.png
└── 7.png
└── 8.png
└── 9.png
└── 10.png
└── 11.png
└── 12.png
└── 13.png
└── 14.png
└── 15.png
└── 16.png
└── 17.png
└── 18.png
└── classes and subclasses.png # Protégé hierarchy or query view
└── End