HUMAN MOBILITY PATTERN CLUSTERING USING GPS TRAJECTORY DATA FOR SMART TRAFFIC MONITORING AND CONGESTION ANALYSIS

Urban transportation systems generate large volumes of spatial-temporal data through GPS-enabled devices.Analyzing this trajectory data enables understanding of mobility behavior, congestion patterns, and accidentprone regions.This research proposes a machine learning-based framework for clustering human mobility patterns using GPS trajectory data.Travel speed is computed using the Haversine distance formula, and spatial clustering is performed using DBSCAN to detect dense movement regions without requiring predefined cluster counts.The Elbow method with K-Means clustering is applied to validate optimal cluster separation.The system further identifies congestion zones based on cluster density and average speed analysis.Accident-prone coordinates are integrated into the visualization layer for safety monitoring.The implementation is carried out using Python and interactive geospatial mapping tools.Experimental results demonstrate that the proposed approach effectively detects mobility hotspots and traffic zones.The framework provides a scalable and costeffective solution for smart city transportation analytics and real-time mobility monitoring.