Skip to content

Falkonry Time Series Intelligence (TSI)

AI Modeling with Insights

Falkonry Time Series Intelligence (TSI)

Home
Introduction
Introduction
User Guide
User Guide
- Introduction
- Administration
  Administration
  - Account Management
  - User Management
  - API Access Maangement
  - Private Storage
  - Connections
    Connections
    
    Overview
    
    Inbound Connections
    
    Outbound Connections
- Signals Management
  Signals Management
- Reports
  Reports
  - Overview
  - Organize and Locate Reports
  - Insights Reports
  - Sharing Reports
  - Report Widget Types
    Report Widget Types
    
    Overview
    
    Notes Widget
    
    Timeline Widget
    
    Signal Value Distributions (SVD) Widget
- Rules & Alerts
  Rules & Alerts
- Calculations Transform
  Calculations Transform
  - Overview
- Insights Anomaly Detection
  Insights Anomaly Detection
- Patterns Classification
  Patterns Classification
Tutorials
Tutorials
- Quick Start
- Managing Signals
- Managing Rules
- AI Modeling with Insights AI Modeling with Insights
  Table of contents
  - Creating a Baseline Model
  - Revising an Anomaly Model
- AI Modeling with Patterns
- Create ROC signals with Calculations Transform
- Create an Asset Incident Library
APIs Reference
APIs Reference
- Overview
- Administration
  Administration
- Signals Management
  Signals Management
- Reports
  Reports
  - Create a custom report
  - Deep linking
- Rules & Alerts
- Calculations Transform
- Insights Anomaly Detection
  Insights Anomaly Detection
  - Model Management
- Patterns Classification
  Patterns Classification
  - Entities
- Live Monitoring
- Integrations
  Integrations
  - Alert Notification via email using Zapier Integration
  - Custom Integration with Falkonry Rules
Resources
Resources
- Glossary
  Glossary
  - Time Series
  - Falkonry TSI Terms
- Best Practices
- Chart Gestures
- Search using Regex
- FAQ
- User Forum
Troubleshooting
Troubleshooting
- General
- API
- Patterns
- Insights
- Calculations Transform
- Rules

Building an Anomaly Detection Model using Falkonry Insights¶

Creating a Baseline Model¶

How to create a univariate baseline anomaly detection model with:

Select a numeric signal that has consistent data with good sampling rate (>100 mHz recommended)
Identify the baseline normal behavior period (learning range) represented in the selected signal
Run an ANOMALYLEARN flow. Once complete, review the output of the model.
1. When the output contains gaps, it is likely that the input data has missing values or irregular sampling. Consider revising the learning range to select a period where there is more consistent data in the input signal.
2. For lower latency change the aperture setting to something smaller (non-default). Consult Falkonry Experts before settling on a non-default aperture.
Capture the Model ID from the flow response for the model that has satisfactory results
Use the Signal ID and the Model ID to start live monitoring.

Revising an Anomaly Model¶

Coming Soon