← Back to Projects Manufacturing / IoT 
IoT Anomaly Detection System
Unsupervised anomaly detection for manufacturing IoT sensors using Isolation Forest, PyTorch Autoencoders, and DBSCAN with real-time scoring and alerting.
Overview
Unsupervised anomaly detection system for manufacturing IoT sensor data with real-time scoring.
Architecture
- Isolation Forest for statistical anomaly detection
- PyTorch Autoencoder for reconstruction-based detection
- DBSCAN for clustering-based outlier identification
- Real-time scoring simulation with async processing
- Configurable alerting thresholds
Key Features
- Multi-model anomaly ensemble
- Root cause analysis visualization
- Configurable alert rules and thresholds
- Interactive sensor monitoring dashboard