A multi-sensor data fusion pipeline with a real-time hazard detection model achieving 98% AUC-ROC, shortlisted for Smart India Hackathon 2025.
Multi-sensor fusion pipeline for real-time geological hazard detection, running inference at the edge on live monitoring data.
Fusion before classification
Several sensor streams are fused into a single view of slope state before anything classifies it. That ordering is the point of the system: individual channels are too noisy to trigger on, and the correlations between them are what actually carry the signal.
A model tuned for the cost of being wrong
Hazard detection is a heavily imbalanced problem where a miss and a false alarm cost wildly different amounts. AUC-ROC is reported because it measures separability across every threshold rather than accuracy at one convenient cut-off; the model reaches 98%.
Inference at the edge
The model runs on edge hardware next to the sensors rather than in a cloud service, so detection survives the connectivity that monitoring sites actually have and the alert path has no network in its critical section.
Real-time, meaning continuous
The pipeline consumes live monitoring data continuously rather than scoring batches, which is what makes the output a warning rather than a report.
Multi-sensor fusion
Correlating channels that mean nothing alone.
Real-time detection
Continuous scoring of live monitoring data.
Edge deployment
Inference where connectivity cannot be assumed.
Measured separability
98% AUC-ROC rather than a single-threshold accuracy.
Result: 98% AUC-ROC
Recognition: SIH 2025 shortlist
Inference: At the edge
Divyakush Punjabi