How codingguna/enhanced-fault-node-detection-in-environmental-monitoring-wsn works
The product is a real-time environmental WSN fault-monitoring system. Sensor readings are simulated or supplied by nodes, sent to a Flask API, checked by a three-layer detector, persisted, and exposed to a live dashboard; separate training and evaluation flows support the ML capability. The README documents the end-to-end flow, while some route internals and dashboard implementation details were not sampled, so those links rely on documented behavior.
Main entry points: server.py Flask API · hybrid_detector.py Hybrid Detector · ml_trainer.py Model Trainer · db_manager.py Database Access
Components 20
Sensor Ingestion
- Node Simulator
testing_environment/node_simulator.py - Simulator Client
sensor_client.py
Fault Detection
- Cluster Peer Cache
server.py - Hybrid Detector
detection_system/hybrid_detector.py - Rule Checks
detection_system/hybrid_detector.py - Cluster Checks
detection_system/hybrid_detector.py - ML Inference
detection_system/hybrid_detector.py - Decision Fusion
detection_system/hybrid_detector.py
Persistence and API
- Flask API
server.py - Payload Validation
server.py - Database Access
database/db_manager.py - SQLite Store
database/wsn_detections.db
ML Lifecycle
- Training Dataset
database/wsn_aft_dataset.csv - Model Trainer
detection_system/ml_trainer.py - Model Artifacts
models - ML Metrics
evaluation/ml_metrics.json - Evaluation Report
evaluation/generate_report.py
Monitoring Experience
- Live Dashboard
static/dashboard.html
Other components
- Sensor Nodes
- Dashboard User
Connections 26
- Sensor Nodes → Node Simulator: simulated by
README.md - Node Simulator → Simulator Client: generates readings
sensor_client.py - Simulator Client → Flask API: POSTs readings
sensor_client.py - Sensor Nodes → Flask API: sends readings
- Flask API → Payload Validation: validates payload
server.py - Flask API → Cluster Peer Cache: updates peers
server.py - Flask API → Hybrid Detector: runs detection
README.md - Cluster Peer Cache → Hybrid Detector: provides peers
server.py - Hybrid Detector → Rule Checks: checks thresholds
README.md - Hybrid Detector → Cluster Checks: checks peer anomalies
README.md - Hybrid Detector → ML Inference: classifies readings
README.md - Rule Checks → Decision Fusion: votes in
detection_system/hybrid_detector.py - Cluster Checks → Decision Fusion: votes in
detection_system/hybrid_detector.py - ML Inference → Decision Fusion: votes in
detection_system/hybrid_detector.py - Flask API → Database Access: stores result
README.md - Database Access → SQLite Store: writes and queries
database/db_manager.py - Flask API → Database Access: queries status and history
server.py - Model Trainer → Training Dataset: loads dataset
detection_system/ml_trainer.py - Model Trainer → Model Artifacts: saves model files
detection_system/ml_trainer.py - Model Trainer → ML Metrics: writes metrics
detection_system/ml_trainer.py - Hybrid Detector → Model Artifacts: loads classifier
detection_system/hybrid_detector.py - Evaluation Report → Training Dataset: evaluates dataset
evaluation/generate_report.py - Evaluation Report → Model Artifacts: loads trained artifacts
evaluation/generate_report.py - Dashboard User → Live Dashboard: views
README.md - Live Dashboard → Flask API: fetches live data
README.md - Flask API → ML Metrics: serves metrics
server.py