Investigate phase !

The Investigate Phase in an AI project is all about ensuring the problem is well-defined, the data is usable, and the approach is viable before investing in model development

Meet the Team

We are engineering students specializing in Artificial Intelligence, passionate about using technology to solve real-world problems. Our team, SynapTech, is composed of:

• Aziza Naffati
• Khouloud Kechim
• Islem Ben Mansour
• Amine Mnif
• Amal Ben Amor
• Yassine Hemissi
• Ibtissem Ayedi

Together, we bring a mix of technical expertise, creativity, and determination to develop cutting-edge AI solutions.

Sedaya Insect Detection Using AI

1. What is the Sedaya Insect? Why is Early Detection Important?

The Sedaya insect (Oligonychus afrasiaticus) is a tiny spider mite that attacks date palms, causing severe crop damage.
Early detection is crucial because:

• The mite reproduces rapidly and spreads easily.
• It damages fruits by sucking out plant fluids, leading to shriveling and discoloration.
• Economic losses occur due to decreased crop yield and quality.

2. Impact on Agriculture & Environment

• ** Agriculture:** Reduces market value and crop yield.
• ** Environment:** Excessive pesticide use harms beneficial insects, disrupts ecosystems, and contaminates soil & water.

3. AI & Deep Learning for Detection

AI enables early detection & prediction through:

• Image Recognition: Identifies infestations on fruits & leaves.
• Climate Data Analysis: Predicts high-risk infestation periods.
• Machine Learning Models: Improve accuracy over time.

4. Why Predict Early?

Prevents crop losses
Reduces pesticide use, lowering costs & environmental harm
Enhances farmer productivity
Protects future harvests

5. AI Model Training Process

Deep learning techniques used:

• Image classification & object detection (Detecting mites in photos)
• Time-series analysis (Studying environmental conditions)
• Sensor data fusion (Combining various data sources)

6. Required Data for AI Training

Labeled images: Healthy vs. infested date palms
Spectral & thermal imaging: Detecting early stress
Weather conditions: Temperature, humidity, wind speed
Soil & irrigation data: Understanding infestation patterns
Pesticide application records: Studying past treatments

7. Economic Benefits for Farmers & Workers

Prevents revenue loss
Saves money on pesticides
Increases export potential
Optimizes labor costs

8. Challenges & Solutions in Data Collection

9. Contribution to Sustainable Agriculture

Less pesticide use → Protects the environment
Early intervention → Healthier crops
Precision agriculture → Resource efficiency
Supports biodiversity → Saves beneficial insects

10. AI for Smart Pest Management

Real-time alerts for farmers
AI-driven risk assessments
Predictive analytics for future outbreaks
Integrated Pest Management (IPM) recommendations

11. Impact on Food Security & Loss Reduction

Boosts food production, ensuring supply stability
Reduces post-harvest losses, increasing available food
Supports farmer livelihoods
Minimizes waste, saving crops from infestation

12. Community Involvement

Farmers & Agricultural Workers:
Upload images, report infestations via mobile apps
Research Institutions:
Conduct field studies, collect real-world data
Tech Companies & Government:
Deploy IoT sensors for large-scale monitoring

13. Ethical Considerations in AI Agriculture

Data Privacy: Farmers' data must be secure
Bias in AI: Diverse datasets ensure fair predictions
Accessibility: Affordable AI for small-scale farmers
Human-AI Collaboration: AI should assist, not replace, experts

14. Technologies Used

Computer Vision & Deep Learning

How It Works:

• AI models analyze high-resolution images of date palms.

• CNNs (Convolutional Neural Networks) classify healthy vs. infested crops.

• Farmers use AI-powered mobile apps to scan fruits in real-time.

  Tools Used:

• TensorFlow, PyTorch → Model training

• Mobile-based AI apps → Google Lens-style detection

• Edge AI → Real-time, offline analysis

Conclusion

The AI-powered Sedaya detection project provides early pest detection, reduces crop losses, and promotes sustainable agriculture. By integrating deep learning, image analysis, and real-time monitoring, this project helps farmers make data-driven decisions, reducing pesticide dependence and improving food security.

PV of the 3d week - Artificial Intelligence Project (CBL Methodology)

Date: 6/02/2025 Location: Google Meet

👥 Attendees:

• Aziza Neffati
• Amine Mnif
• Yassine Hemissi
• Ibtissem Ayedi
• Islem Ben Mansour
• Amal Ben Amor
• Khouloud Kechim

1️⃣ Opening of the Meeting

Time: 08:00 PM

1. We discussed the two project ideas: the CBL project and the ACTIA project. We talked about each project's advantages and disadvantages.
2. Each person gave their point of view and explained why they were against it or not.
3. The majority voted for the ACTIA project, and we decided to continue working on it.

2️⃣ . Defining the investigate phase

We started discussing the ACTIA project and its objectives. We started doing a research about cybersecurity attacks and its types.

3️⃣ Conclusion

In conclusion, during the meeting, we discussed and compared the two project ideas: the CBL project and the ACTIA project. Each team member shared their perspective, explaining their stance on each idea. After evaluating the advantages and disadvantages, the majority voted in favor of the ACTIA project. As a result , we decided to proceed with this project and began discussing its objectives and key aspects for development.

📝 PV of the Second Meeting - Artificial Intelligence Project (CBL Methodology)

Date: 7/02/2025
Location: Google Meet

👥 Attendees:

• Aziza Neffati
• Amine Mnif
• Yassine Hemissi
• Ibtissem Ayedi
• Islem Ben Mansour
• Amal Ben Amor
• Khouloud Kechim

1️⃣ Opening of the Meeting

Time: 07:30 PM
2. We discussed again the two project ideas: the CBL project and the ACTIA project. We talked about each project's advantages and disadvantages. 3. Each person gave their point of view and explained why they were against it or not. 4. The majority voted for the Cedia project, and we decided to continue working on it.

2️⃣ Defining the investigate phase

We started discussing the Cedia project and its objectives, and we began conducting research on Cedia

3️⃣ Conclusion

In conclusion, during the meeting, we discussed and compared the two project ideas: the CBL project and the ACTIA project. Each team member shared their perspective, explaining their stance on each idea. After evaluating the advantages and disadvantages, the majority voted in favor of the cedia project. As a result, we decided to proceed with this project and began discussing its objectives and key aspects for development.

📝 PV of the Third Meeting - Artificial Intelligence Project (CBL Methodology)

Date: 8/02/2025
Location: Google Meet

👥 Attendees:

• Aziza Neffati
• Amine Mnif
• Yassine Hemissi
• Ibtissem Ayedi
• Islem Ben Mansour
• Amal Ben Amor
• Khouloud Kechim

during the meeting

Time: 07:00 PM
• We discussed again the investigate phase: • We started making questions about cedia ; • What is the Cedia insect, and how does it spread? According to what criteria? • What are the causes and symptoms of Cydia? • the ways of spread of Cydia by air or Which plants do mites live on, and how can they be prevented? • What are the species of mites that attack date palms?" • "What are the visible symptoms on dates and infested palms?" • "What environmental factors favor their proliferation?" • "What is the current extent of the problem in date-growing areas?" • Which date palm varieties are less susceptible to Oligonychus afrasiaticus infestations? • Why are some date palm varieties more resistant to mite attacks? • How does fruit cuticle thickness influence resistance to mite infestations? • What role do tannins and polyphenols play in protecting date palms from mites? • How does the maturation cycle of dates impact their susceptibility to Oligonychus afrasiaticus?