[2/3] Media preparation (two types) for anomaly detection (crops data set)
Workflow Description
Advanced workflow for preparing two distinct media types for anomaly detection in crop datasets. Combines manual triggers, HTTP requests, and custom code logic to process raw media data into normalized training datasets.
How it works
- 1.Initiate workflow manually and retrieve initial media data via HTTP request from data source
- 2.Split media into two separate type-based streams and apply specialized processing logic to each
- 3.Merge processed results into unified output format ready for anomaly detection model
Use cases
- Prepare multi-source crop images and sensor data for plant health anomaly detection systems
- Standardize heterogeneous media inputs before applying machine learning anomaly models
Requirements
- HTTP-accessible media data sources with clear type classification and metadata
- Development capability to customize processing logic for each media type's unique characteristics
Service Value
Ready-made workflow template for automation delivery and service execution.
Apps Used
Details
How to Use
- 1.Click "Download Template"
- 2.Open your n8n dashboard
- 3.Go to Workflows > Import from File
- 4.Select downloaded file and configure credentials
Nodes Used (48)
When clicking ‘Test workflow’
Manual Trigger
Total Points in Collection
HTTP Request
Cluster Distance Matrix
HTTP Request
Scipy Sparse Matrix
Code
Set medoid id
HTTP Request
Get Medoid Vector
HTTP Request
Prepare for Searching Threshold
Set
Searching Score
HTTP Request
Threshold Score
Set
Set medoid threshold score
HTTP Request
Split Out1
Split Out
Merge
Merge
Textual (visual) crop descriptions
Set
Embed text
HTTP Request
Get Medoid by Text
HTTP Request
Set text medoid id
HTTP Request
Prepare for Searching Threshold1
Set
Threshold Score1
Set
Searching Text Medoid Score
HTTP Request
Medoids Variables
Set
Text Medoids Variables
Set
Qdrant cluster variables
Set
Info About Crop Clusters
Set
Crop Counts
HTTP Request
Sticky Note
Sticky Note
Sticky Note1
Sticky Note
Sticky Note2
Sticky Note
Sticky Note3
Sticky Note
Sticky Note4
Sticky Note
Sticky Note5
Sticky Note
Sticky Note6
Sticky Note
Sticky Note8
Sticky Note
Sticky Note9
Sticky Note
Split Out
Split Out
Sticky Note10
Sticky Note
Sticky Note11
Sticky Note
Sticky Note12
Sticky Note
Sticky Note13
Sticky Note
Sticky Note14
Sticky Note
Set text medoid threshold score
HTTP Request
Sticky Note15
Sticky Note
Sticky Note16
Sticky Note
Sticky Note17
Sticky Note
Sticky Note18
Sticky Note
Sticky Note19
Sticky Note
Sticky Note20
Sticky Note
Sticky Note21
Sticky Note
Sticky Note22
Sticky Note