Setup Medoids for Anomaly Detection in Crop Data

• Detect anomalies in agricultural crop data using clustering techniques.
• Identify representative crop points for better data analysis.
• Set threshold scores for effective anomaly detection in crop datasets.

Initiate the workflow with a manual trigger. Fetch total points from the Qdrant database. Calculate cluster distance matrices for crop data. Determine medoids using Python for matrix operations. Set threshold scores for identified medoids to facilitate anomaly detection.

1. 1
   Import the workflow template into your n8n instance.
2. 2
   Click 'Test workflow' to trigger the initial data fetch.
3. 3
   Configure Qdrant cluster variables for your specific dataset.
4. 4
   Run the workflow to set up medoids and threshold scores.