Case study · AI/ML · Data

Adaptive Traffic Signaling — with Bangalore Traffic Police

LSTM-based traffic optimisation engine that learns from high-frequency, real-time sensor streams to adapt signal timing, built in collaboration with Bangalore Traffic Police.

30%

Less congestion (simulated)

00 How it works

How it works

Cameras detect and count every vehicle at each approach

01 The problem

Fixed-time traffic signals can't react to real traffic, so junctions stay congested while green time is spent on empty roads.

02 Approach

01
Ingested high-frequency, real-time traffic sensor streams.
02
Trained LSTM neural networks to forecast traffic flow and adapt signal timing.
03
Optimised backend database queries to keep up with continuous sensor ingestion.

03 Architecture

01Traffic sensorsreal-time ingestion pipelineSQL store

02Recent flow historyLSTM forecastersignal-timing optimiser

04 Results

30% reduction in congestion in simulation.
Backend sustained continuous, high-frequency sensor ingestion.

Next case study

Product Carbon Footprint Engine