Redermamana Redermamana

Hybrid CNN LSTM Deep Learning Model for Spatiotemporal Traffic Accident Risk Prediction in Medan City with Localized Urban Traffic Patterns

A Hybrid CNN–LSTM Deep Learning Model is proposed that jointly learns spatial features from georeferenced accident maps, road networks, and traffic density heatmaps, and temporal dependencies from historical accident logs, GPS traces, meteorological data, and road surface conditions, enabling robust performance under h...